hillclimb
Member of Technical Staff - Environments & Post-Training
$300K
San Francisco · On-site · Staff · Full-time · Posted Sep 28, 2026
About the job
Design and validate training environments and evaluations, then run post-training experiments to identify which environments can train models effectively.
What you'll do
- Translate ML research problems into environments that reward meaningful progress and good research taste.
- Test whether environment rewards are repeatable and accurately measure work quality.
- Build systems to create and validate environments at scale, and run post-training experiments.
Nice to have
- Experience with LLMs, RL, RLHF/RLAIF, RLVR, post-training, evals, graders, synthetic data, model training, or coding agents at a frontier/data lab.
- Understanding of trustworthy reward evaluation and how models exploit weak evaluations; experience designing automated environment-building and quality-checking systems.
Pay
$300K (base salary); 3% – 5% (compensation type not stated)
Tools
LLMs, RL, RLHF/RLAIF, RLVR
AI focus
Develop and evaluate environments and post-training methods to improve model research capabilities.
Model-written summary · the original posting is authoritative