Preference Model
Member of Technical Staff - Research Engineer, RL Environments
$200K–$350K
San Francisco · On-site · Staff · Full-time · Posted Oct 19, 2026
- Experience
- 5+ years in machine learning or research, primarily on LLMs and transformer models.
- Visa sponsorship
- Visa sponsorship and relocation support available
About the job
Designs and builds reinforcement learning environments and reward functions that train frontier models on machine learning research and engineering tasks.
What you'll do
- Design, implement, evaluate, and deliver RL environments for production training runs.
- Research and develop new approaches, tools, and ideas to improve environment building.
- Build expertise in frontier ML research, training, and inference infrastructure and collaborate with researchers and engineers.
What they ask for
- 5+ years of experience in machine learning or research, primarily on LLMs and transformer models.
- Strong ML fundamentals and ability to translate research topics into RLVR problems.
- Proficiency in Python and systems programming, plus at least one of PyTorch or JAX.
- Ability to take ownership and drive solutions end-to-end.
Nice to have
- Expertise in an active DL/ML research area, with publications or public code; research experience (PhD, MS) is a plus.
- Experience with transformer internals, modern LLM training/inference, inference libraries, kernel development, or complex interactive RL environments.
Pay
USD $200K – $350K base salary; USD $0 to $300K+ bonus range based on performance
Tools
Python, PyTorch, JAX, vLLM, SGLang, CUDA, Triton, Pallas
AI focus
Build RL environments and reward functions to advance frontier model capabilities in ML research and engineering, with an emphasis on safe training.
Model-written summary · the original posting is authoritative