Member of Technical Staff - Research Engineer, Post-training
Preference Model · San Francisco
Infrastructureonsite$200k–$350k
At a glance
Highlights
- Train and evaluate models on proprietary RL environments to validate quality.
- Push the frontier of self-directed learning for future LLM post-training.
- Design RL environments and evaluations for increasingly capable agents.
What they 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 and dental benefits
- 401K match
- Lunch provided everyday onsite
- Weekly snack orders
- Visa sponsorship & relocation support available
Ideal candidate
An adaptable ML researcher-engineer who loves fast iteration and owns problems end-to-end, balancing exploration with rigor while collaborating and communicating clearly in a fast-moving startup.
Requirements
- Industry experience running end-to-end LLM post-training pipelines for 7B+ models
- Proficiency in Python and PyTorch or JAX
- Experience with at least one modern RL training framework
- Experience building and operating ML infrastructure at scale
- visa sponsorship
- Visa sponsorship & relocation support 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