Vmax
Member of Technical Staff - Applied RL
$300K–$500K
San Francisco +1 · Staff · Full-time · Posted Nov 5, 2025
- Location
- San Francisco
San Francisco, California, United States
About the job
Build and improve reinforcement-learning training systems, evaluations, environments, and rewards for language-model-based agents, working across research and engineering.
What you'll do
- Implement RL research ideas, including reward functions, verifiers, environments, rollout pipelines, and evaluation harnesses.
- Design experiments and monitoring tools to assess model behavior and catch regressions or reward hacking.
- Debug training and learning issues, and build reliable, reusable infrastructure for RL workflows.
What they ask for
- Demonstrated practical ML engineering ability through shipped systems, open-source projects, competitions, independent projects, or equivalent experience.
- Hands-on experience building, training, evaluating, or debugging ML systems.
- Strong Python programming and experience with at least one major ML framework, such as PyTorch or JAX.
- Working understanding of reinforcement learning, supervised learning, optimization, and modern deep learning.
Nice to have
- Experience supporting research teams or fast-moving ML teams.
- Expertise in experiment tracking, evaluation platforms, dataset/versioning systems, or reproducibility infrastructure.
Pay
$300,000 - $500,000 USD (base salary)
Tools
Python, PyTorch, JAX
AI focus
Applied reinforcement learning for language-model-based agents, including post-training methods and evaluation of model behavior, sample efficiency, robustness, and generalization.
Model-written summary · the original posting is authoritative