Member of Technical Staff - Research Engineer, RL Environments
Preference Model · San Francisco
Infrastructureonsitesenior$200k–$350k
At a glance
Highlights
- Build RL environments that train capable, better-aligned superintelligences.
- Teach frontier models to do the work of ML engineers and researchers.
- Own environments end-to-end from design to production training runs.
What they offer
- Competitive cash and equity compensation (>90th percentile)
- Health, vision and dental benefits
- 401K match
- Daily onsite lunch and weekly snack orders
- Relocation support available
Ideal candidate
Experienced ML engineer with deep research curiosity who loves translating cutting-edge papers into learnable RL problems. You take end-to-end ownership, move fast on feedback, and want to shape how superintelligent models behave.
Requirements
- 5+ years of experience working in machine learning or research, primarily on LLMs and transformer models
- Strong ML fundamentals and broad research interests with ability to translate papers into RLVR problems
- Proficiency in Python and systems programming and at least one of PyTorch or JAX
- Takes ownership and drives solutions end-to-end
- Ability to meet throughput expectations and respond quickly to feedback
- visa sponsorship
- Visa sponsorship available
Lab profile
About Preference Model
Superintelligence data research company building RL environments for capable, better-aligned AI.
What they build
- RL environments for superintelligence training
Known for
- Reinforcement learning environments
- Reward signals for capability and alignment
Posted · Last seen