Research Engineer - Inference is open at PrimeIntellect in San Francisco. The posting gives no salary; similar roles in the United States advertise a median of $194K. Posted on Oct 16, 2026, and still on PrimeIntellect’s careers page when we last checked, on Nov 14, 2026.
About the role
Extend prime-rl’s vLLM integration to bring new model architectures into RL training, with small-scale validation before larger runs. - Improve rollout throughput for long-horizon agents, tuning concurrency and KV-cache reuse as context lengths grow. - Optimize multi-node MoE inference, including expert parallelism and the tradeoffs of separating prefill from decode. - Reduce trainer-to-inference weight-update…
The opening lines of the posting. The rest is on PrimeIntellect’s careers page.
Hiring at PrimeIntellect
PrimeIntellect has 38 open roles right now, 3 of them remote. Most are in Engineering, Data & Research and Finance & Trading. See all its roles
