Get Started
Hunting for you, 24x7Get the iPhone app

Your hunt runs in your pocket, and tells you the moment a strong match opens.

Download on theApp Store
Preference ModelPosted in November 2026

Member of Technical Staff - Research Engineer, Post-training

Who we'd reach at Preference ModelFound and reached by Power Apply
Best leadTeam lead

Runs the team day to day

Recruiter

In-house, owns the opening

Recent hire

Joined the team recently

Power Apply

From your own Gmail and LinkedIn.

About the role

This is a full-time research engineering role in San Francisco, California, focused on post-training large language models with reinforcement learning. The engineer works at a company that builds RL environments used to train AI models, blending research and engineering. The work includes training and evaluating models on the company's RL environments, building training infrastructure and designing evaluations and training methods.

What you’ll do

  • Train and evaluate models on proprietary RL environments to check data quality and find gaps in task coverage.
  • Design and build RL training infrastructure, from training abstractions to distributed experiment management, using frameworks such as Verl or OpenRLHF.
  • Help the systems scale to more complex research workflows.
  • Design, implement and test training environments, evaluations and methods for RL agents.
  • Profile and speed up training runs, from data loading through reward computation.

What they’re looking for

  • Industry experience running end-to-end LLM post-training pipelines on models of at least 7B parameters.
  • Proficiency in Python and in PyTorch or JAX.
  • Experience with at least one modern RL training framework.
  • Experience building and operating ML infrastructure at scale.
  • A PhD or extensive publication record is not required.

Nice to have

  • Experience evaluating model outputs and building reward or evaluation signals.
  • Keeping up with post-training research and turning papers into working code.
  • Strong opinions on structuring RL training code for reproducibility and fast iteration.
  • Ability to balance research exploration with engineering rigor.
  • Strong systems design and communication skills.

What’s on offer

  • Cash and equity compensation described as above the 90th percentile.
  • Health, vision and dental coverage, and a 401K match.
  • Lunch provided daily onsite and weekly snack orders.
  • Visa sponsorship and relocation support available.
  • Ownership and autonomy in a fast-moving startup environment.

Skills

Reinforcement learningLLM post-trainingPyTorchJAXPythonVerlOpenRLHFDistributed trainingReward modelingModel evaluationML infrastructureSystems design

Questions about this role

How much does it pay?

The listed range is $200K-$350K, with cash and equity compensation described as above the 90th percentile.

Is a PhD required?

No, the posting says candidates do not need a PhD or extensive publications.

Is visa sponsorship available?

Yes, visa sponsorship and relocation support are available.