Preference Model is a superintelligence data research company. We build RL environments for training capable, better-aligned superintelligences.
Almost every aspect of how a model behaves is shaped by the reward signals it's trained on. The biggest problem with AIs today is that they don't always do what we intend. Sometimes that's because they aren't capable enough, and sometimes it's because they aren't aligned. Both problems come down to the training objectives.
We're trying to address both of these issues in the most direct, highest leverage way available to us, which today means researching how to build RL environments better, not just for the AIs of today but for the AIs as they will be when they outsmart us.
Over the past year, we've built RL environments for several frontier labs, and we're backed by $16M in seed funding led by a16z. Our founding team has previous experience on Anthropic’s data team building data infrastructure, and datasets behind Claude.
We’re hiring new graduate Machine Learning Engineers to design and build reinforcement learning environments to safely advance model capabilities in machine learning research and engineering. Specifically, you'll be teaching frontier models to do the work of an ML engineer or researcher at a frontier lab.
This role blends research and engineering. It will require you to stay up to date with the latest research, develop novel approaches, and realize them in code. You will have full ownership and autonomy of the environments you build. Your work will include designing and implementing RL environments, conducting experiments and evaluations, delivering your work into production training runs, and collaborating with other researchers and engineers.
You will join our Capabilities org, a small, high-ownership team and contribute directly to the data layer that powers frontier LLM capability.
Note: this role is for recent graduates only who can start soon.
Design and build RL environments and reward schemes that produce clean, learnable signals for frontier models on ML research and engineering tasks.
Build deep expertise across the frontier of ML research, training, and inference infrastructure.
Collaborate with others to brainstorm and create new ideas and tools to improve the environment building process.
You have strong ML fundamentals and broad research interests. You read many papers or tutorials, understand topics deeply and have the creativity to translate them into RLVR problems.
Expert knowledge in an active DL/ML research area, with publications or public code to show for it.
Research experience (PhD, MS) is a strongly preferred.
Deep understanding of transformer internals
Proficiency in Python, Numpy, and systems programming; ideally PyTorch or JAX
Smart problem solvers who take ownership and drives solutions end-to-end
Passion for staying current with the rapidly evolving ML infrastructure landscape
Ability to meet throughput expectations and respond quickly to feedback
Strong expertise in kernel development (CUDA, Triton, Pallas), optimizing non-trivial neural modules to specific hardware
Research projects, coursework, or personal work involving RL environments (any framework, any scale)
Open-source contributions to ML infrastructure or RL tooling
Experience with any cloud platform (AWS, GCP, Azure) or infrastructure-as-code tools
Competitive cash and equity compensation (>90th percentile)
Ownership and autonomy in a fast moving startup environment
Opportunity to work with top machine learning engineers
Health, vision, dental, benefits
401K match
Lunch provided everyday onsite
Weekly snack orders
Visa sponsorship & relocation support available
We value diverse perspectives and experiences. If you're excited about this role but don't check every box, we still encourage you to apply.
","descriptionPlain":"ABOUT US\n\nPreference Model is a superintelligence data research company. We build RL environments for training capable, better-aligned superintelligences.\n\nAlmost every aspect of how a model behaves is shaped by the reward signals it's trained on. The biggest problem with AIs today is that they don't always do what we intend. Sometimes that's because they aren't capable enough, and sometimes it's because they aren't aligned. Both problems come down to the training objectives.\n\nWe're trying to address both of these issues in the most direct, highest leverage way available to us, which today means researching how to build RL environments better, not just for the AIs of today but for the AIs as they will be when they outsmart us.\n\nOver the past year, we've built RL environments for several frontier labs, and we're backed by $16M in seed funding led by a16z. Our founding team has previous experience on Anthropic’s data team building data infrastructure, and datasets behind Claude.\n\n\n\n\nABOUT THE ROLE\n\nWe’re hiring new graduate Machine Learning Engineers to design and build reinforcement learning environments to safely advance model capabilities in machine learning research and engineering. Specifically, you'll be teaching frontier models to do the work of an ML engineer or researcher at a frontier lab.\n\nThis role blends research and engineering. It will require you to stay up to date with the latest research, develop novel approaches, and realize them in code. You will have full ownership and autonomy of the environments you build. Your work will include designing and implementing RL environments, conducting experiments and evaluations, delivering your work into production training runs, and collaborating with other researchers and engineers.\n\nYou will join our Capabilities org, a small, high-ownership team and contribute directly to the data layer that powers frontier LLM capability.\n\nNote: this role is for recent graduates only who can start soon.\n\n\n\n\nWHAT YOU WILL DO:\n\n - Design and build RL environments and reward schemes that produce clean, learnable signals for frontier models on ML research and engineering tasks.\n\n - Build deep expertise across the frontier of ML research, training, and inference infrastructure.\n\n - Collaborate with others to brainstorm and create new ideas and tools to improve the environment building process.\n\n\nWHAT WE ARE LOOKING FOR (QUALIFICATIONS):\n\n - You have strong ML fundamentals and broad research interests. You read many papers or tutorials, understand topics deeply and have the creativity to translate them into RLVR problems.\n\n - Expert knowledge in an active DL/ML research area, with publications or public code to show for it. \n \n - Research experience (PhD, MS) is a strongly preferred.\n\n - Deep understanding of transformer internals\n\n - Proficiency in Python, Numpy, and systems programming; ideally PyTorch or JAX\n\n - Smart problem solvers who take ownership and drives solutions end-to-end\n\n - Passion for staying current with the rapidly evolving ML infrastructure landscape\n\n - Ability to meet throughput expectations and respond quickly to feedback\n\n\nNICE TO HAVE:\n\n - Strong expertise in kernel development (CUDA, Triton, Pallas), optimizing non-trivial neural modules to specific hardware\n\n - Research projects, coursework, or personal work involving RL environments (any framework, any scale)\n\n - Open-source contributions to ML infrastructure or RL tooling\n\n - Experience with any cloud platform (AWS, GCP, Azure) or infrastructure-as-code tools\n\n\nWHAT WE OFFER:\n\n - Competitive cash and equity compensation (>90th percentile)\n\n - Ownership and autonomy in a fast moving startup environment\n\n - Opportunity to work with top machine learning engineers\n\n - Health, vision, dental, benefits\n\n - 401K match\n\n - Lunch provided everyday onsite\n\n - Weekly snack orders\n\n - Visa sponsorship & relocation support available\n\n\n\nWe value diverse perspectives and experiences. If you're excited about this role but don't check every box, we still encourage you to apply."},{"id":"9729e0f8-678d-4548-992b-0b0028cc50c6","title":"Member of Technical Staff - Machine Learning Capabilities","department":"Engineering","team":"Engineering","employmentType":"FullTime","location":"San Francisco","secondaryLocations":[],"publishedAt":"2026-09-11T23:23:55.670+00:00","isListed":true,"isRemote":false,"workplaceType":"OnSite","address":{"postalAddress":{"addressRegion":"California","addressCountry":"United States","addressLocality":"San Francisco"}},"jobUrl":"https://jobs.ashbyhq.com/preference-model/9729e0f8-678d-4548-992b-0b0028cc50c6","applyUrl":"https://jobs.ashbyhq.com/preference-model/9729e0f8-678d-4548-992b-0b0028cc50c6/application","descriptionHtml":"Preference Model is a superintelligence data research company. We build RL environments for training capable, better-aligned superintelligences.
Almost every aspect of how a model behaves is shaped by the reward signals it's trained on. The biggest problem with AIs today is that they don't always do what we intend. Sometimes that's because they aren't capable enough, and sometimes it's because they aren't aligned. Both problems come down to the training objectives.
We're trying to address both of these issues in the most direct, highest leverage way available to us, which today means researching how to build RL environments better, not just for the AIs of today but for the AIs as they will be when they outsmart us.
Over the past year, we've built RL environments for several frontier labs, and we're backed by $16M in seed funding led by a16z. Our founding team has previous experience on Anthropic’s data team building data infrastructure, and datasets behind Claude.
We’re hiring experienced Machine Learning Engineers to design and build reinforcement learning environments to safely advance model capabilities in machine learning research and engineering. Specifically, you'll be teaching frontier models to do the work of an ML engineer or researcher at a frontier lab.
This role blends research and engineering. It will require you to stay up to date with the latest research, develop novel approaches, and realize them in code. You will have full ownership and autonomy of the environments you build. Your work will include designing and implementing RL environments, conducting experiments and evaluations, delivering your work into production training runs, and collaborating with other researchers and engineers.
You will join our Capabilities org, a small, high-ownership team and contribute directly to the data layer that powers frontier LLM capability.
Note: This role is only for experienced ML Engineers. We have a separate opening for New Grads.
Design and build RL environments and reward functions that produce clean, learnable signals for frontier models on ML research and engineering tasks
Build deep expertise across the frontier of ML research, training, and inference infrastructure
Collaborate with others to brainstorm and create new ideas and tools to improve the environment building process
5+ years of experience working in machine learning or research, primarily on LLMs and transformer models
You have strong ML fundamentals and broad research interests. You read many papers or tutorials, understand topics deeply and have the creativity to translate them into RLVR problems
Proficiency in Python and systems programming and at least one of PyTorch or JAX
Problem solvers who take ownership and drives solutions end-to-end
Passion for staying current with the rapidly evolving ML infrastructure landscape
Ability to meet throughput expectations and respond quickly to feedback
Have expert knowledge in an active DL/ML research area, with publications or public code to show for it. Research experience (PhD, MS) is a big plus
Have deep understanding of transformer internals, training/inference of modern LLMs, experience with inference libraries (vLLM, SGLang, etc)
Have strong expertise in kernel development (CUDA, Triton, Pallas)
Have built complex interactive RL environments
Competitive cash and equity compensation (>90th percentile)
Ownership and autonomy in a fast moving startup environment
Opportunity to work with top machine learning engineers
Health, vision, dental, benefits
401K match
Lunch provided everyday onsite
Weekly snack orders
Visa sponsorship & relocation support available
We value diverse perspectives and experiences. If you're excited about this role but don't check every box, we still encourage you to apply.
","descriptionPlain":"ABOUT US\n\nPreference Model is a superintelligence data research company. We build RL environments for training capable, better-aligned superintelligences.\n\nAlmost every aspect of how a model behaves is shaped by the reward signals it's trained on. The biggest problem with AIs today is that they don't always do what we intend. Sometimes that's because they aren't capable enough, and sometimes it's because they aren't aligned. Both problems come down to the training objectives.\n\nWe're trying to address both of these issues in the most direct, highest leverage way available to us, which today means researching how to build RL environments better, not just for the AIs of today but for the AIs as they will be when they outsmart us.\n\nOver the past year, we've built RL environments for several frontier labs, and we're backed by $16M in seed funding led by a16z. Our founding team has previous experience on Anthropic’s data team building data infrastructure, and datasets behind Claude.\n\n\n\n\nABOUT THE ROLE\n\nWe’re hiring experienced Machine Learning Engineers to design and build reinforcement learning environments to safely advance model capabilities in machine learning research and engineering. Specifically, you'll be teaching frontier models to do the work of an ML engineer or researcher at a frontier lab.\n\nThis role blends research and engineering. It will require you to stay up to date with the latest research, develop novel approaches, and realize them in code. You will have full ownership and autonomy of the environments you build. Your work will include designing and implementing RL environments, conducting experiments and evaluations, delivering your work into production training runs, and collaborating with other researchers and engineers.\n\nYou will join our Capabilities org, a small, high-ownership team and contribute directly to the data layer that powers frontier LLM capability.\n\nNote: This role is only for experienced ML Engineers. We have a separate opening for New Grads https://jobs.ashbyhq.com/Preference-Model/44642065-e592-44ba-810d-a019703463b6.\n\n\n\n\nWHAT YOU WILL DO:\n\n - Design and build RL environments and reward functions that produce clean, learnable signals for frontier models on ML research and engineering tasks\n\n - Build deep expertise across the frontier of ML research, training, and inference infrastructure\n\n - Collaborate with others to brainstorm and create new ideas and tools to improve the environment building process\n\n\nWHAT WE ARE LOOKING FOR (QUALIFICATIONS):\n\n - 5+ years of experience working in machine learning or research, primarily on LLMs and transformer models\n\n - You have strong ML fundamentals and broad research interests. You read many papers or tutorials, understand topics deeply and have the creativity to translate them into RLVR problems\n\n - Proficiency in Python and systems programming and at least one of PyTorch or JAX\n\n - Problem solvers who take ownership and drives solutions end-to-end\n\n - Passion for staying current with the rapidly evolving ML infrastructure landscape\n\n - Ability to meet throughput expectations and respond quickly to feedback\n\n\nYOU MAY BE A GOOD FIT IF YOU ALSO:\n\n - Have expert knowledge in an active DL/ML research area, with publications or public code to show for it. Research experience (PhD, MS) is a big plus\n\n - Have deep understanding of transformer internals, training/inference of modern LLMs, experience with inference libraries (vLLM, SGLang, etc)\n\n - Have strong expertise in kernel development (CUDA, Triton, Pallas)\n\n - Have built complex interactive RL environments\n\n\nWHAT WE OFFER:\n\n - Competitive cash and equity compensation (>90th percentile)\n\n - Ownership and autonomy in a fast moving startup environment\n\n - Opportunity to work with top machine learning engineers\n\n - Health, vision, dental, benefits\n\n - 401K match\n\n - Lunch provided everyday onsite\n\n - Weekly snack orders\n\n - Visa sponsorship & relocation support available\n\n\n\nWe value diverse perspectives and experiences. If you're excited about this role but don't check every box, we still encourage you to apply."},{"id":"22f5bbbc-1459-4915-97c8-cda18046ec31","title":"Member of Technical Staff - Research Engineer, Post-training","department":"Engineering","team":"Engineering","employmentType":"FullTime","location":"San Francisco","secondaryLocations":[],"publishedAt":"2026-09-11T23:24:44.032+00:00","isListed":true,"isRemote":false,"workplaceType":"OnSite","address":{"postalAddress":{"addressRegion":"California","addressCountry":"United States","addressLocality":"San Francisco"}},"jobUrl":"https://jobs.ashbyhq.com/preference-model/22f5bbbc-1459-4915-97c8-cda18046ec31","applyUrl":"https://jobs.ashbyhq.com/preference-model/22f5bbbc-1459-4915-97c8-cda18046ec31/application","descriptionHtml":"Preference Model is a superintelligence data research company. We build RL environments for training capable, better-aligned superintelligences.
Almost every aspect of how a model behaves is shaped by the reward signals it's trained on. The biggest problem with AIs today is that they don't always do what we intend. Sometimes that's because they aren't capable enough, and sometimes it's because they aren't aligned. Both problems come down to the training objectives.
We're trying to address both of these issues in the most direct, highest leverage way available to us, which today means researching how to build RL environments better, not just for the AIs of today but for the AIs as they will be when they outsmart us.
Over the past year, we've built RL environments for several frontier labs, and we're backed by $16M in seed funding led by a16z. Our founding team has previous experience on Anthropic’s data team building data infrastructure, and datasets behind Claude.
Models of the future will be able to train themselves on tasks that they are not good at. We are interested in investigating how far we can push the boundaries of self-directed learning. We are looking for machine learning Research Engineers or Research Scientists to push the frontier of post-training on large language models in a role that blends research and engineering, requiring you to implement novel approaches and shape research directions.
Train and evaluate models on our proprietary RL environments to validate data quality, surface gaps in task coverage, and close the feedback loop between environment design and model capability.
Architect and optimize our RL training infrastructure, from training abstractions to distributed experiment management, using frameworks like Verl, OpenRLHF, or similar. Help scale our systems to handle increasingly complex research workflows.
Design, implement, and test training environments, evaluations, and methodologies for RL agents.
Profile and optimize training runs end-to-end, from data loading through reward computation, to maximize experiment throughput and shorten the research iteration cycle.
Experience running end-to-end LLM post-training pipelines of models sizes at least 7B in size
Proficiency in Python and PyTorch or JAX
Experience with at least one modern RL training framework
Experience building and operating ML infrastructure at scale
Have experience evaluating model outputs and building reward or evaluation signals
Stay current on post-training research and can translate papers into running code
Have strong opinions (loosely held) about how to structure RL training code for reproducibility and fast iteration
Can balance research exploration with engineering rigor
Have strong systems design and communication skills
Candidates don't need a PhD or extensive publications. Some of the best researchers have no formal ML training and gained experience building industry products. We believe adaptability combined with exceptional communication and collaboration skills are the most important ingredients for successful startup research.
Competitive cash and equity compensation (>90th percentile)
Ownership and autonomy in a fast moving startup environment
Opportunity to work with top machine learning engineers
Health, vision, dental, benefits
401K match
Lunch provided everyday onsite
Weekly snack orders
Visa sponsorship & relocation support available
We value diverse perspectives and experiences. If you're excited about this role but don't check every box, we still encourage you to apply.
","descriptionPlain":"ABOUT US\n\nPreference Model is a superintelligence data research company. We build RL environments for training capable, better-aligned superintelligences.\n\nAlmost every aspect of how a model behaves is shaped by the reward signals it's trained on. The biggest problem with AIs today is that they don't always do what we intend. Sometimes that's because they aren't capable enough, and sometimes it's because they aren't aligned. Both problems come down to the training objectives.\n\nWe're trying to address both of these issues in the most direct, highest leverage way available to us, which today means researching how to build RL environments better, not just for the AIs of today but for the AIs as they will be when they outsmart us.\n\nOver the past year, we've built RL environments for several frontier labs, and we're backed by $16M in seed funding led by a16z. Our founding team has previous experience on Anthropic’s data team building data infrastructure, and datasets behind Claude.\n\n\n\n\nABOUT THE ROLE\n\nModels of the future will be able to train themselves on tasks that they are not good at. We are interested in investigating how far we can push the boundaries of self-directed learning. We are looking for machine learning Research Engineers or Research Scientists to push the frontier of post-training on large language models in a role that blends research and engineering, requiring you to implement novel approaches and shape research directions.\n\n\n\n\nWHAT YOU WILL DO:\n\n - Train and evaluate models on our proprietary RL environments to validate data quality, surface gaps in task coverage, and close the feedback loop between environment design and model capability.\n\n - Architect and optimize our RL training infrastructure, from training abstractions to distributed experiment management, using frameworks like Verl, OpenRLHF, or similar. Help scale our systems to handle increasingly complex research workflows.\n\n - Design, implement, and test training environments, evaluations, and methodologies for RL agents.\n\n - Profile and optimize training runs end-to-end, from data loading through reward computation, to maximize experiment throughput and shorten the research iteration cycle.\n \n \n\n\nWHAT WE ARE LOOKING FOR\n\n - Experience running end-to-end LLM post-training pipelines of models sizes at least 7B in size\n\n - Proficiency in Python and PyTorch or JAX\n\n - Experience with at least one modern RL training framework\n\n - Experience building and operating ML infrastructure at scale\n\n\n\n\nYOU MAY BE A GOOD FIT IF YOU ALSO:\n\n - Have experience evaluating model outputs and building reward or evaluation signals\n\n - Stay current on post-training research and can translate papers into running code\n\n - Have strong opinions (loosely held) about how to structure RL training code for reproducibility and fast iteration\n\n - Can balance research exploration with engineering rigor\n\n - Have strong systems design and communication skills\n\nCandidates don't need a PhD or extensive publications. Some of the best researchers have no formal ML training and gained experience building industry products. We believe adaptability combined with exceptional communication and collaboration skills are the most important ingredients for successful startup research.\n\n\n\n\nWHAT WE OFFER:\n\n - Competitive cash and equity compensation (>90th percentile)\n\n - Ownership and autonomy in a fast moving startup environment\n\n - Opportunity to work with top machine learning engineers\n\n - Health, vision, dental, benefits\n\n - 401K match\n\n - Lunch provided everyday onsite\n\n - Weekly snack orders\n\n - Visa sponsorship & relocation support available\n\nWe value diverse perspectives and experiences. If you're excited about this role but don't check every box, we still encourage you to apply."},{"id":"96e7f7d7-3fb5-48d8-ba18-a7ebce54a9be","title":"Member of Technical Staff - ML Infrastructure Engineer, Post-training","department":"Engineering","team":"Engineering","employmentType":"FullTime","location":"San Francisco","secondaryLocations":[],"publishedAt":"2026-09-11T23:25:31.918+00:00","isListed":true,"isRemote":false,"workplaceType":"OnSite","address":{"postalAddress":{"addressRegion":"California","addressCountry":"United States","addressLocality":"San Francisco"}},"jobUrl":"https://jobs.ashbyhq.com/preference-model/96e7f7d7-3fb5-48d8-ba18-a7ebce54a9be","applyUrl":"https://jobs.ashbyhq.com/preference-model/96e7f7d7-3fb5-48d8-ba18-a7ebce54a9be/application","descriptionHtml":"Preference Model is a superintelligence data research company. We build RL environments for training capable, better-aligned superintelligences.
Almost every aspect of how a model behaves is shaped by the reward signals it's trained on. The biggest problem with AIs today is that they don't always do what we intend. Sometimes that's because they aren't capable enough, and sometimes it's because they aren't aligned. Both problems come down to the training objectives.
We're trying to address both of these issues in the most direct, highest leverage way available to us, which today means researching how to build RL environments better, not just for the AIs of today but for the AIs as they will be when they outsmart us.
Over the past year, we've built RL environments for several frontier labs, and we're backed by $16M in seed funding led by a16z. Our founding team has previous experience on Anthropic’s data team building data infrastructure, and datasets behind Claude.
Frontier research moves only as fast as its infrastructure permits. Building solid infrastructure is foundational to our mission of pushing self-directed learning as far as it can go.
We are looking for Senior ML Infrastructure Engineers to build the infrastructure and systems that power the frontier of post-training on large language models. This role involves building scalable infrastructure to enable high-throughput systems and shape how our research is run, bringing us closer to models that can train themselves on what they aren't yet good at.
Design, build, and scale the compute, scheduling, and data infrastructure that powers post-training research on our in-house RL environments
Develop and maintain core ML framework primitives and internal tooling that researchers rely on daily, accelerating reproducible experimentation and reducing time from idea to result
Build evaluation and benchmarking infrastructure, monitoring, logging, and debugging tooling, and automated testing and deployment systems, so failures are caught early and infrastructure stays reliable as it scales
Partner directly with Research Engineers to translate research needs into infrastructure requirements, and ship fast in response to their feedback
Strong software engineering fundamentals and hands-on experience building production-grade LLM inference and training infrastructure (ideally from the ground up)
Experience building LLM training/inference internals such as transformers, distributed training, and working on inference libraries like vLLM, SGLang, Megatron
Experience working on RL training frameworks like Slime, veRL, Ray Train, SkyRL
Significant experience and understanding of distributed systems principles, and have hands-on experience with cloud platforms (AWS, GCP) and container orchestration (Kubernetes), building systems for high-throughput, low-latency workloads
Have experience with data engineering tools and building robust, scalable data pipelines
Proficiency in core ML frameworks such as PyTorch or JAX
Can balance production rigor with the pace of fast-moving research, and communicate infrastructure tradeoffs clearly to researchers who aren't infra specialists
Competitive cash and equity compensation (>90th percentile)
Ownership and autonomy in a fast moving startup environment
Opportunity to work alongside senior and staff engineers from frontier labs and infrastructure companies, plus top ML engineers
Health, vision, dental, benefits
401K match
Lunch provided everyday onsite
Weekly snack orders
Visa sponsorship & relocation support available
We value diverse perspectives and experiences. If you're excited about this role but don't check every box, we still encourage you to apply.
","descriptionPlain":"ABOUT US\n\nPreference Model is a superintelligence data research company. We build RL environments for training capable, better-aligned superintelligences.\n\nAlmost every aspect of how a model behaves is shaped by the reward signals it's trained on. The biggest problem with AIs today is that they don't always do what we intend. Sometimes that's because they aren't capable enough, and sometimes it's because they aren't aligned. Both problems come down to the training objectives.\n\nWe're trying to address both of these issues in the most direct, highest leverage way available to us, which today means researching how to build RL environments better, not just for the AIs of today but for the AIs as they will be when they outsmart us.\n\nOver the past year, we've built RL environments for several frontier labs, and we're backed by $16M in seed funding led by a16z. Our founding team has previous experience on Anthropic’s data team building data infrastructure, and datasets behind Claude.\n\n\n\n\nABOUT THE ROLE\n\nFrontier research moves only as fast as its infrastructure permits. Building solid infrastructure is foundational to our mission of pushing self-directed learning as far as it can go. \n\nWe are looking for Senior ML Infrastructure Engineers to build the infrastructure and systems that power the frontier of post-training on large language models. This role involves building scalable infrastructure to enable high-throughput systems and shape how our research is run, bringing us closer to models that can train themselves on what they aren't yet good at.\n\n \n\n\nWHAT YOU WILL DO\n\n - Design, build, and scale the compute, scheduling, and data infrastructure that powers post-training research on our in-house RL environments\n\n - Develop and maintain core ML framework primitives and internal tooling that researchers rely on daily, accelerating reproducible experimentation and reducing time from idea to result\n\n - Build evaluation and benchmarking infrastructure, monitoring, logging, and debugging tooling, and automated testing and deployment systems, so failures are caught early and infrastructure stays reliable as it scales\n\n - Partner directly with Research Engineers to translate research needs into infrastructure requirements, and ship fast in response to their feedback\n \n\n\nWHAT WE ARE LOOKING FOR\n\n - Strong software engineering fundamentals and hands-on experience building production-grade LLM inference and training infrastructure (ideally from the ground up)\n\n - Experience building LLM training/inference internals such as transformers, distributed training, and working on inference libraries like vLLM, SGLang, Megatron\n\n - Experience working on RL training frameworks like Slime, veRL, Ray Train, SkyRL\n\n - Significant experience and understanding of distributed systems principles, and have hands-on experience with cloud platforms (AWS, GCP) and container orchestration (Kubernetes), building systems for high-throughput, low-latency workloads\n\n - Have experience with data engineering tools and building robust, scalable data pipelines\n\n - Proficiency in core ML frameworks such as PyTorch or JAX\n\n - Can balance production rigor with the pace of fast-moving research, and communicate infrastructure tradeoffs clearly to researchers who aren't infra specialists\n\n\n\n\nWHAT WE OFFER:\n\n - Competitive cash and equity compensation (>90th percentile)\n\n - Ownership and autonomy in a fast moving startup environment\n\n - Opportunity to work alongside senior and staff engineers from frontier labs and infrastructure companies, plus top ML engineers\n\n - Health, vision, dental, benefits\n\n - 401K match\n\n - Lunch provided everyday onsite\n\n - Weekly snack orders\n\n - Visa sponsorship & relocation support available\n\n\n\nWe value diverse perspectives and experiences. If you're excited about this role but don't check every box, we still encourage you to apply."}],"apiVersion":"1"}