Staff ML Engineer: Inference & Optimization Lead

Nebius is building production-grade inference for open-source, customer, and internally optimized models. This role owns the path from model artifact to fast, reliable endpoints, sitting at the intersection of model internals, inference engines, serving architecture, benchmarking, and deployment.

You will drive platform-level optimizations and build reusable evaluation and rollout frameworks across model families, collaborating with MLEs, engineers, and researchers to meet strict latency and