Member of Technical Staff - Research Engineer, Post-training

Preference Model

  • San Francisco, CA
  • On-site
  • Senior level
  • Machine Learning Engineering
  • Sponsors visas
  • $200k–$350k

The role in 30 seconds

Preference Model is a superintelligence data research company building RL environments for training capable, better-aligned superintelligences. We are looking for machine learning Research Engineers or Research Scientists to push the frontier of post-training on large language models, blending research and engineering to implement novel approaches and shape research directions.

Is this role a fit for you?

The backgrounds this role is most likely to hire from, as RoleStack reads the posting.

Strong match

  • Software, SaaS & AI Platform
  • B2B infrastructure / API / developer tools
  • Growth-stage
  • Startup / greenfield

Workable stretch

  • Internal tooling / back-office systems
  • B2B enterprise platform / workflow software
  • Creator / builder / self-serve tool
  • Enterprise-scale

Harder transition

  • B2C consumer-facing application
  • Marketplace / multi-sided platform
  • Embedded systems / hardware-adjacent
  • Data platform / ML pipeline
  • Regulated environment

Industry: Software, SaaS & AI Platform. See your personal match score

What they're really screening for

Must-haves

  • CORE Industry experience running end-to-end LLM post-training pipelines of models sizes at least 7B in size
  • CORE Proficiency in Python and PyTorch or JAX
  • CORE Experience with at least one modern RL training framework
  • CORE Experience building and operating ML infrastructure at scale

Nice-to-haves

  • PLUS Experience evaluating model outputs and building reward or evaluation signals
  • PLUS Stay current on post-training research and can translate papers into running code
  • PLUS Have strong opinions (loosely held) about how to structure RL training code for reproducibility and fast iteration
  • PLUS Can balance research exploration with engineering rigor
  • PLUS Have strong systems design and communication skills

Résumé keywords for this role

Terms the posting stresses. Include the ones you can honestly back up.

Tools & technologies

  • Preference Model
  • RL
  • LLM
  • Python
  • PyTorch
  • JAX
  • Verl
  • OpenRLHF
  • ML

Concepts & phrases

  • Member of Technical Staff
  • Research Engineer
  • Post-training
  • superintelligence data research company
  • RL environments
  • trained on
  • reward signals
  • AI today
  • what we intend
  • training objectives
  • frontier labs
  • seed funding
  • founding team
  • data team
  • data infrastructure

Words that count as the same thing: "post-training" ≈ model tuning, fine-tuning · "RL" ≈ Reinforcement Learning · "LLM" ≈ Large Language Model

Check my résumé against these keywords

Hiring at Preference Model

Open senior roles RoleStack tracks right now, posted in the last 30 days.

More open roles at Preference Model

Full job description from Preference Model

From Preference Model's posting. View the original

ABOUT US

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.

Show full description Show less

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.

ABOUT THE ROLE

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.

WHAT YOU WILL DO:

- 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.

WHAT WE ARE LOOKING FOR

- Industry 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

YOU MAY BE A GOOD FIT IF YOU ALSO:

- 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.

WHAT WE OFFER:

- 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.

FAQ

How much does a Member of Technical Staff - Research Engineer, Post-training at Preference Model make?

The posted pay for this role is $200k–$350k a year.

Does Preference Model sponsor visas for this role?

The posting says visa sponsorship is available.

Is this role remote?

It is an on-site role.

What tools and technologies does the posting mention?

Preference Model, RL, LLM, Python, PyTorch, JAX, Verl, OpenRLHF, ML.