Staff ML Engineer - Inference Platform & Optimization
Posted Updated
Description
Nebius is building production-grade inference for open-source, customer, and internally optimized models. You will own the path from model artifact to fast, reliable, cost-efficient endpoints at platform level, interfacing with MLEs, GPU kernel engineers, and infrastructure teams.
You will optimize end-to-end latency, throughput, and memory usage, deploy engines such as vLLM, TensorRT-LLM, or Triton, and drive reproducible benchmarks across multiple model families.
Own platform-level optimization pillars such as quantization or long-context serving. Create reusable evaluation, benchmarking, and rollout frameworks for multiple model families. Provide technical direction to engineers on performance goals. Optimize LLM and VLM endpoints for latency, throughput, memory, GPU usage, cost per token. Deploy and benchmark inference engines (e.g., vLLM, Triton). Strong Python and PyTorch engineering skills. Hands-on experience deploying or optimizing LLM/VLM inference systems. Competitive compensation Career growth and learning Flexibility and ownership Collaborative culture Work on impactful AI projects International environmentSkills
Sign in to read and join the discussion.