All jobs
Senior Machine Learning Engineer, LLM Inference Optimization
Nebius
Berlin +1 · Remote possibleSenior (5–10 years)Full-timePosted 15 days ago
About the job
What you'll do
You will own the optimization of model and endpoint performance, focusing on latency, throughput, and cost-efficiency for frontier AI models. This involves working across the full stack to diagnose bottlenecks, implement inference engines, and deliver measurable production improvements.
What they're looking for
Candidates must have strong Python and PyTorch engineering skills with hands-on experience in deploying or optimizing high-throughput transformer inference systems. A deep understanding of inference bottlenecks and familiarity with modern stacks like vLLM or TensorRT-LLM is essential.
Full description