Research Engineer, RL Frontiers

What you’d do

Research engineer on the RL Frontiers team, post-training proprietary frontier models to automate kernel development, ASIC engineering, and hardware operating systems. You own the post-training stack end to end and build RL environments and benchmarks with engineering teams. Found on the employer's careers page on Oct 21, 2026. Apply through the link.

You’ll need

• RL or post-training frameworks (verl, OpenRLHF, TRL, prime-rl)
• Inference engines (vLLM, SGLang)
• Agentic multi-turn RL with verifiable rewards
• Distillation and small specialized model training
• ASIC design, accelerator kernels, or large-scale compute