Senior ML Engineer - LLM Inference & Optimization

Nebius Group; Amsterdam; Teletrabalho; EUR 90 000 - 150 000; Tempo integral

Vantagens oferecidas por esta oferta de emprego

Competitive compensation

Career growth and learning

Flexibility and ownership

Collaborative culture

Impactful AI projects

International environment

Resumo da oferta

Nebius Group, a leading AI cloud platform, invites a Senior Machine Learning Engineer to own model and endpoint optimization from artifacts through production deployment. You will work on quantization, speculative decoding, KV-cache optimization, and multi-node GPU execution to boost latency, throughput, and memory efficiency.

You will collaborate with kernel and platform engineers to diagnose bottlenecks, evaluate distributed inference designs, and validate improvements under real-world

Qualificações

• Strong engineering skills in Python and PyTorch.
• Hands-on experience deploying or optimizing LLM/VLM or high-throughput transformer inference.
• Experience with modern inference stacks such as vLLM, TensorRT-LLM, Triton Inference Server, or KServe.
• Understanding of transformer bottlenecks like KV cache, attention, memory bandwidth and batching.

Responsabilidades

• Own optimization projects for specific model families and endpoints.
• Compare inference engines and recommend configurations for workloads.
• Diagnose model-quality and performance regressions in production.
• Improve LLM/VLM endpoint latency, throughput, and cost per token.
• Deploy and benchmark engines such as vLLM, TensorRT-LLM, and Triton.
• Develop workflows for model compression and quantization workflows.

Conhecimentos

Python

PyTorch

LLM optimization

Distributed inference

Performance tuning

GPU optimization

Quantization

Ferramentas

vLLM

SGLang

TensorRT-LLM

Triton Inference Server

NVIDIA Dynamo

Ray Serve

KServe

Descrição da oferta de emprego

Nebius Group, a leading AI cloud platform, invites a Senior Machine Learning Engineer to own model and endpoint optimization from artifacts through production deployment. You will work on quantization, speculative decoding, KV-cache optimization, and multi-node GPU execution to boost latency, throughput, and memory efficiency.

You will collaborate with kernel and platform engineers to diagnose bottlenecks, evaluate distributed inference designs, and validate improvements under real-world