GPU Infrastructure / Performance Engineer London (Onsite) | Visa Sponsorship + Relocation
Join a frontier AI company backed by NVIDIA, building large-scale open-weight foundation models alongside researchers and engineers from DeepMind, OpenAI, Meta, Anthropic, and Google Brain.
⚡ What You’ll Do Optimise GPU performance and training efficiency across 1,000+ GPU clusters Improve utilisation, throughput, and reliability across distributed training infrastructure Build tooling for orchestration, monitoring, scheduling, and observability Work closely with research teams to accelerate large-scale model training
What They’re Looking For Deep GPU infrastructure / distributed systems experience Strong knowledge of CUDA, NCCL, PyTorch, DeepSpeed, JAX, Megatron-LM, vLLM, etc. Experience operating large-scale GPU clusters (1,000+ GPUs) Kubernetes, Slurm, or similar orchestration expertise
BONUS: Experience working on NVIDIA Blackwell chips (B200, B300, GB200, GB300)
Package Salary open to candidate expectations Meaningful startup equity Full visa sponsorship + relocation support…