Staff ML Engineer: Inference & Performance

Nebius Group; Amsterdam; On-site; EUR 120,000 - 190,000; Full time

Benefits offered by this job

Competitive compensation

Career growth and learning opportunity

Flexibility and ownership

Collaborative and innovative culture

International environment and talented

Job summary

Nebius Group is building a production-grade AI cloud platform in Amsterdam, focusing on scalable inference for open-source and optimized models. The role oversees model artifact to cost-efficient endpoints, intersecting model internals, inference engines, and deployment.

You will drive performance improvements, collaborate with ML engineers and infrastructure teams, and help deploy and benchmark cutting-edge inference stacks in a fast-moving environment.

Qualifications

• Strong Python and PyTorch engineering skills.
• Experience deploying or optimizing LLM, VLM, or high-throughput transformer inference systems.
• Practical knowledge of at least one modern inference stack such as vLLM, SGLang, TensorRT-LLM, Triton Inference Server, NVIDIA Dynamo, Ray Serve, or KServe.
• Strong understanding of transformer inference bottlenecks, including KV cache, attention, memory bandwidth, batching, parallelism, and long-context serving.
• Ability to reason quantitatively about latency, throughput, quality, utilization, and cost tradeoffs.
• Strong communication skills and ability to collaborate with research, kernel, infrastructure, product, and customer teams.

Responsibilities

• Own a platform-level optimization pillar such as quantization, speculative decoding, KV-cache optimization, engine selection, or long-context serving.
• Create reusable evaluation, benchmarking, and rollout frameworks across multiple model families.
• Provide technical direction to MLEs, Applied Scientists, GPU kernel engineers, and infrastructure engineers on shared performance goals.
• Optimize LLM and VLM endpoints for latency, throughput, memory efficiency, GPU utilization, quality, and cost per token.
• Deploy, configure, benchmark, and extend inference engines such as vLLM, SGLang, TensorRT-LLM, Triton Inference Server, NVIDIA Dynamo, or similar systems.
• Build and productionize model-compression workflows, including quantization, quantization-aware training, distillation, low-bit serving, and accuracy recovery.
• Implement or integrate speculative decoding, draft-model approaches, KV-cache optimization, prefix caching, chunked prefill, continuous batching, and disaggregated prefill/decode serving.
• Build reproducible benchmark harnesses for TTFT, TPOT, tokens per second per GPU, p95/p99 latency, GPU memory, reliability, and cost per token.
• Partner with GPU kernel engineers and platform engineers to diagnose bottlenecks across model code, kernels, runtime, scheduler, gateway, and cluster layers.
• Write clear design docs, performance reports, rollout plans, and customer-facing technical explanations.

Skills

Python programming

PyTorch engineering

Performance optimization

Cross-team collaboration

Technical communication

Tools

vLLM

SGLang

TensorRT-LLM

Triton Inference Server

NVIDIA Dynamo

Ray Serve

KServe

Job description

Nebius Group is building a production-grade AI cloud platform in Amsterdam, focusing on scalable inference for open-source and optimized models. The role oversees model artifact to cost-efficient endpoints, intersecting model internals, inference engines, and deployment.

You will drive performance improvements, collaborate with ML engineers and infrastructure teams, and help deploy and benchmark cutting-edge inference stacks in a fast-moving environment.