Staff Machine Learning Engineer, LLM Inference Optimization

Overview

Nebius is offering an employment opportunity for a Staff Machine Learning Engineer specializing in LLM Inference Optimization. The position is based in Zurich, Switzerland, within the Europe region. The role focuses on building production-grade inference for open-source, customer, and internally optimized models, taking model artifacts to fast, reliable, and cost-efficient endpoints.

Requirements

Applicants need strong Python and PyTorch engineering skills alongside practical knowledge of modern inference stacks such as vLLM, SGLang, TensorRT-LLM, Triton Inference Server, NVIDIA Dynamo, Ray Serve, KServe, or equivalent internal systems. Candidates must also have hands-on experience deploying or optimizing LLM, VLM, or high-throughput transformer inference systems. A strong understanding of transformer inference bottlenecks, quantitative reasoning regarding performance and cost tradeoffs, and solid communication skills for cross-functional collaboration are required. Furthermore, applicants must be authorized to work in the country where they apply and provide proof of employment eligibility upon hire.

What you get

Selected candidates receive competitive compensation, flexibility and ownership, and career growth and learning opportunities. The role operates within a collaborative, innovative, and international environment focused on impactful AI projects.