Research, Tinker, RL Systems
San Francisco
Workplace: HybridFull timeUSD 350,000 - 475,000 annuallyFunction: Research & Scientific (R&D)Skills: ["Communication","Debugging","Problem-solving","Technical writing"]Build post-training reinforcement learning (RL) systems for a fine-tuning platform, spanning RL algorithms, numerics, kernels, and end-to-end training pipelines. Work with internal researchers and external partners to co-design whole-stack training approaches, debug RL runs, and optimize stability and performance so users can achieve frontier-level results. Use Python with deep learning frameworks while engaging directly with researchers pushing Tinker to its limits.
Loading
Loading job details...
Preparing the role view and application actions.

