Preference Model
Member of Technical Staff - Research Engineer, Post-training
$200K–$350K
San Francisco · On-site · Staff · Full-time · Posted Oct 19, 2026
- Experience
- Industry experience running end-to-end LLM post-training pipelines for models at least 7B in size; no years specified.
- Education
- Candidates don't need a PhD or extensive publications.
- Visa sponsorship
- Visa sponsorship & relocation support available
About the job
Research and engineer post-training methods for large language models, including RL environments, evaluations, and scalable training infrastructure.
What you'll do
- Train and evaluate models on proprietary RL environments to assess data quality and task coverage.
- Build and optimize RL training infrastructure and distributed experiment management.
- Design and test training environments, evaluations, and RL methodologies; profile runs to improve throughput.
What they ask for
- Industry experience running end-to-end LLM post-training pipelines for models 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.
Nice to have
- Experience evaluating model outputs and building reward or evaluation signals.
- Stay current on post-training research and translate papers into running code.
Pay
$200K – $350K (base salary); Offers Equity
Tools
Python, PyTorch, JAX, Verl, OpenRLHF
AI focus
Investigate self-directed learning and advance post-training of large language models through RL environments, training methods, and evaluations.
Model-written summary · the original posting is authoritative