Mirendil
Member of Technical Staff, Post-Training, RL Infra
$300K–$400K
San Francisco · On-site · Staff · Full-time · Posted Jun 24, 2026
About the job
Build and scale the post-training infrastructure used to train frontier reasoning models with reinforcement learning.
What you'll do
- Design reliable infrastructure for large-scale RL training and optimize training-stack performance.
- Develop evaluation and benchmarking systems for model progress, throughput, and uptime.
- Build data and feedback pipelines and collaborate on RL algorithms and production training experiments.
Pay
$300,000–$400,000 USD base salary
AI focus
Build infrastructure and pipelines for reinforcement learning post-training of frontier reasoning models, including evaluation, feedback, and performance optimization.
Model-written summary · the original posting is authoritative