About this job
<p style="min-height:1.5em">You'll own how Luma's models get served — integrating new architectures into the inference engine, scaling deployments across thousands of machines, and keeping expensive GPU fleets busy while meeting internal SLOs.</p><p style="min-height:1.5em">This is large-scale inference systems work: scheduling, fleet management, deployment pipelines, and reliability across clusters and hardware providers. It fits a strong systems engineer comfortable with model serving and Kubernetes at scale. If you want pure modeling rather than the systems that run models, this is firmly the systems side.</p><p style="min-height:1.5em"><strong>What You'll Own</strong></p><ul style="min-height:1.5em"><li><p style="min-height:1.5em">Ship new model architectures by integrating them into the inference engine.</p></li><li><p style="min-height:1.5em">Collaborate across research, engineering, and infrastructure to optimize model efficiency and deployments.</p></li><li><p style="min-height:1.5em">Build internal tooling to measure, profile, and track the lifetime of inference jobs and workflows.</p></li><li><p style="min-height:1.5em">Automate, test, and maintain inference services for maximum uptime and reliability.</p></li><li><p style="min-height:1.5em">Manage and optimize inference workloads across clusters and hardware providers, and scale deployments across thousands of machines.</p></li><li><p style="min-height:1.5em">Build scheduling systems that use expensive GPU resources optimally while meeting SLOs, and maintain CI/CD for model checkpoints and SDKs.</p></li></ul><p style="min-height:1.5em"><strong>First 90 Days</strong></p><p style="min-height:1.5em"><em>One way the first 90 could unfold.</em></p><ul style="min-height:1.5em"><li><p style="min-height:1.5em"><strong>Days 1–30 — Immerse & Diagnose:</strong> Learn the inference stack, the fleets, and where reliability or utilization break.</p></li><li><p style="min-height:1.5em"><strong>Days 30–60 — Ship & Validate:</strong> Integrate a model or ship tooling/scheduling that improves uptime or GPU utilization.</p></li><li><p style="min-height:1.5em"><strong>Days 60–90 — Scale & Systemize:</strong> Harden deployment pipelines and scheduling across clusters and providers.</p></li></ul><p style="min-height:1.5em"><strong>What You Bring</strong></p><ul style="min-height:1.5em"><li><p style="min-height:1.5em">Strong Python and system-architecture skills.</p></li><li><p style="min-height:1.5em">Experience deploying models with PyTorch, Hugging Face, vLLM, SGLang, TensorRT-LLM, or similar.</p></li><li><p style="min-height:1.5em">Experience with queues, scheduling, traffic control, and fleet management at scale.</p></li><li><p style="min-height:1.5em">Experience with Linux, Docker, and Kubernetes, and with orchestration, deployment, and scheduling.</p></li><li><p style="min-height:1.5em">Familiarity with Redis and S3-compatible storage.</p></li></ul><p style="min-height:1.5em"><strong>Nice to Have</strong></p><ul style="min-height:1.5em"><li><p style="min-height:1.5em">Modern networking stacks including RDMA (RoCE, InfiniBand, NVLink).</p></li><li><p style="min-height:1.5em">High-performance large-scale ML systems (100+ GPUs).</p></li><li><p style="min-height:1.5em">CUDA, and FFmpeg or multimedia processing.</p></li></ul><p style="min-height:1.5em"><em>About Luma: Luma's mission is to build unified general intelligence that can generate, understand, and operate in the physical world. We believe multimodality is critical for intelligence — the next step beyond language models comes from vision. Luma is an equal opportunity employer.</em></p><p>Find more <a href="https://www.arbeitnow.co.uk/english-speaking-jobs">English Speaking Jobs in United Kingdom</a> on Arbeitnow</a>