All opportunities

Career opportunity

Prime Intellect

Research Engineer - Inference

Apply for this role (opens in a new tab)

The opportunity

About this role

Build and optimize GPU inference systems for reinforcement-learning research at frontier scale. Work on vLLM integrations, long-horizon rollout throughput, multi-node MoE inference, low-precision inference, and performance debugging.

Skills & focus areas

  • machine-learning
  • inference
  • GPU
  • reinforcement-learning
  • AI-research

Explore your next step in AI, data & engineering.

Machinoai Logo
Machinoai

Your edge in the AI era. Deep dives into machine learning concepts, paper explainers, verified industry jobs, and developer tools.

© 2026 Machinoai. All rights reserved.