Senior ML Engineer (Token Factory)

Stack

Responsibilities

• ▹Identify LLM inference bottlenecks to drive production speedups
• ▹Squeeze maximum performance from a wide range of LLM architectures at scale (e.g. GPT-OSS, Kimi K2.5, DeepSeek V3.1/V3.2, GLM-5)
• ▹Support inference engines: implement speculative decoding architectures, optimize LLM design components, contribute to open-source inference engines
• ▹Design and productionize low-precision (FP8, NVFP4/MXFP4) training and inference pipelines

Requirements

• ▹A profound understanding of theoretical foundations of machine learning and transformer architecture
• ▹Experience profiling GPU workloads using Nsight, PyTorch profiler, or similar tools
• ▹Understanding of GPU memory hierarchy and compute/memory tradeoffs
• ▹Familiarity with key ideas in the LLM space: MHA, RoPE, KV-cache, Flash Attention, quantization
• ▹Understanding of performance aspects of large neural network training (sharding strategies, custom kernels, hardware features)
• ▹Strong software engineering skills (mostly Python)
• ▹Deep experience with modern deep learning frameworks
• ▹Proficiency in contemporary software engineering approaches: CI/CD, version control, unit testing
• ▹Strong communication and leadership abilities

Nice to have

• ▹Experience working with open-source inference engines (vLLM, SGLang, TensorRT-LLM), including contributions
• ▹Experience with kernel languages or DSLs such as Triton, Cute, CUTLASS, CUDA
• ▹A track record of building and delivering products in a dynamic startup-like environment
• ▹Experience developing large distributed systems or high-load web services
• ▹Open-source projects that showcase engineering prowess
• ▹Excellent command of English, with superior writing and communication skills

Soft skills

What we offer

• ▹Competitive compensation
• ▹Career growth and learning opportunities
• ▹Flexibility and ownership
• ▹Collaborative and innovative culture
• ▹Opportunity to work on impactful AI projects
• ▹International environment and talented teams

About the company

Nebius is building a full-stack AI cloud platform supporting developers and enterprises from data and model training through production deployment. Listed on Nasdaq (NBIS) and headquartered in Amsterdam, with 1,500+ employees and R&D hubs across Europe, the UK, North America, and Israel.