Senior Machine Learning Engineer, LLM Inference Optimization

On-site · Zurich (Switzerland) · Senior · Full-time

Want offers like this one?

Create your free PyHires profile: you will see how well you match each offer and get a weekly email with the ones that fit you.

Create my profile

Overview

Work mode
On-site
Location
Zurich (Switzerland)
Engagement
Full-time
Seniority
Senior
Languages
English
Open to candidates from
All of Europe (EU and non-EU)
Company
Nebius
Posted
Nov 19, 2026

About the role

Nebius builds a full-stack AI cloud platform, from model training to production deployment. As a Senior Machine Learning Engineer on the Applied AI team at Nebius Token Factory, you will own model and endpoint optimization from model artifacts to production: quantization and compression, speculative decoding, KV-cache optimization, inference engines, serving architecture and benchmarking, improving latency, throughput, GPU utilization and cost per token without losing quality. What you'll do - Own optimization projects for specific model families, customer endpoints or serving backends - Compare inference engines and recommend serving configurations for individual workloads - Diagnose model-quality and performance regressions during production rollouts - Deploy, configure, benchmark and extend engines such as vLLM, SGLang, TensorRT-LLM, Triton Inference Server and NVIDIA Dynamo - Build production model-compression workflows: quantization, quantization-aware training, distillation and low-bit serving - Implement speculative decoding, KV-cache optimization, prefix caching, chunked prefill and continuous batching - Build reproducible benchmark harnesses (TTFT, TPOT, tokens per second per GPU, p95/p99 latency, GPU memory, cost per token) - Work with kernel and platform engineers on distributed inference: request routing, scheduling and multi-node GPU execution What you bring - Strong engineering skills in Python and PyTorch - Practical knowledge of at least one modern inference stack, such as vLLM, SGLang, TensorRT-LLM, Triton, NVIDIA Dynamo, Ray Serve or KServe - Experience designing or optimizing distributed inference architecture: request routing, distributed scheduling, multi-node inference or expert parallelism - Familiarity with GPU communication libraries and interconnects such as NCCL, NVLink, InfiniBand or RoCE What they offer - Impactful AI projects at a fast-growing, Nasdaq-listed AI cloud company

Requirements

Based on:Python

Must-have

  • LLM
  • PyTorchEssential

About Nebius

Nebius builds a full-stack AI cloud platform that supports developers and enterprises from data and model training through to production deployment, covering GPU orchestration, storage, networking and inference optimization. Listed on Nasdaq (NBIS) and headquartered in Amsterdam, it has R&D hubs across Europe, the UK, North America and Israel and a team of more than 1,500 people.

Stack

  • Python
  • LLM
  • PyTorch

Company

Nebius logo
Nebius
Switzerland
View company profile