Research, RL Scaling
San Francisco
Workplace: HybridFull timeUSD 350,000 - 475,000 annuallyFunction: Research & Scientific (R&D)Education: bachelorsSkills: ["Communication","Research judgment","Technical writing"]Scale reinforcement learning for frontier models by co-designing both the RL training recipe and the systems that run it, with an emphasis on asynchronous RL. Work end-to-end from algorithms to parallelism plans, improving rollout-generation efficiency and its integration with training. Optimize accelerator utilization, memory, communication, and low-precision numerics, and conduct careful empirical science through trusted instrumentation, ablations, and scaling studies.
Loading
Loading job details...
Preparing the role view and application actions.

