Find your next role
Discover roles across ambitious teams
12,642 jobs
- More jobs
Nebius
Senior Machine Learning Engineer, LLM Inference Optimization
Remote · Europe, Israel · Senior level
About the role
Optimize model and endpoint performance for LLM inference from artifacts to production deployment. Improve latency, throughput, memory efficiency, GPU utilization, and cost per token while maintaining quality.
What you’ll do
• Own optimization projects for model families and serving backends. • Compare inference engines and recommend configurations. • Diagnose model-quality and performance regressions. • Deploy and benchmark inference engines like vLLM and TensorRT-LLM. • Design LLM request routers and scheduling policies.
What you’ll bring
• Strong Python and PyTorch engineering skills. • Experience deploying or optimizing LLM or transformer inference. • Knowledge of modern inference stacks like vLLM or Triton. • Understanding of transformer inference bottlenecks and trade-offs. • Experience with distributed inference system architecture.
Life at Nebius
Competitive compensation, career growth, flexibility, collaborative culture, international teams, impactful AI projects.
About Nebius
Nebius builds a full-stack AI cloud platform for developers and enterprises, focusing on large-scale GPU orchestration and inference optimization. Listed on Nasdaq with global R&D hubs.