> Markdown version of [/jobs/ext/3520738-staff-software-engineer-inference](https://www.wearedevelopers.com/jobs/ext/3520738-staff-software-engineer-inference). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # Staff Software Engineer, Inference - **Company:** Coreweave's Inference - **Location:** London, UK - **Experience:** Expert - **Contract:** Permanent contract - **Skills:** Artificial Intelligence, Systems Engineering, C++ (Programming Language), Nvidia CUDA, Distributed Systems, Python (Programming Language), Open Source Technology, Performance Tuning, Remote Direct Memory Access, Service Design, Computer Networking Systems, Cloud Platform System, Large Language Models, Kubernetes, Information Technology, Machine Learning Operations, TensorRT - **Published:** October 1, 2026 - **Apply:** https://www.apply4u.co.uk/jobs/staff-software-engineer-inference/49510991 ## About the Role or organisation-level technical initiatives at scale. Strong coding proficiency in Go, Python, or C++. Deep expertise in Kubernetes at production scale, including orchestration, scheduling, and service design. Strong understanding of networked systems, performance optimisation, and distributed system design. Hands-on engineering experience with inference systems, including batching/micro-batching strategies, caching, memory optimisation, mixed precision (BF16/FP8), and streaming token delivery. Demonstrated ability to systematically improve tail latency (P95/P99) and platform reliability through metrics-driven engineering. Proven experience owning system-wide SLIs/SLOs, capacity planning, autoscaling strategies, and mentoring senior and mid-level engineers. Preferred Direct open-source or production contributions to modern inference frameworks (e.g., vLLM, Triton, TensorRT-LLM, Ray Serve, or TorchServe). Deep experience with GPU systems engineering and hardware performance optimisation (e.g., CUDA, NCCL, RDMA, NUMA, or GPU interconnects). Direct exposure to large-scale AI/ML infrastructure or hyperscale cloud environments. Wondering if you're a good fit? We believe in investing in our people, and value candidates who can bring their own diversified experiences to our teams-even if you aren't a 100% skill or experience match. You love to: Scale highly complex distributed architectures and mentor engineering cohorts to elevate technical standards across an organisation. You're curious about: Pioneering low-latency inference optimisations and finding innovative shortcuts to optimise cost-per-token performance. You're an expert in: Metrics-driven engineering, troubleshooting micro-bottlenecks, and delivering stable cloud platforms under strict multi-tenant constraints. Why CoreWeave? At CoreWeave, we work hard, have fun, and move fast! We're in an exciting stage of hyper-growth that you will not want to miss out on. We're not afraid of a little chaos, and we're ## Description Inference team, you will operate as a technical leader across multiple teams and services, driving architecture, performance, and reliability for CoreWeave's Kubernetes-native inference platform. You will define and lead complex, cross-cutting design initiatives spanning request routing, adaptive scheduling, GPU resource management, and cost-per-token optimisation under strict P99 SLAs. In this high-impact role, you will implement advanced inference optimisations-such as speculative decoding and KV-cache reuse-while establishing performance benchmarking frameworks, guiding cross-functional alignment across infrastructure boundaries, and raising the bar for engineering rigour and observability practices across the organisation. Who You Are Bachelor's degree in Computer Science, Engineering, or a related technical field (or equivalent practical experience). 8+ years of experience building large-scale distributed systems or cloud platforms, with a proven track record of leading cross-team ## Related Videos - [Tour de Force: Open-Source LLM Inference Optimization from Simple to Sophisticated](https://www.wearedevelopers.com/videos/100099-tour-de-force-open-source-llm-inference-optimization-from-simple-to-sophisticated) - [Coffee with Developers - Stephen Jones - NVIDIA](https://www.wearedevelopers.com/videos/1303-coffee-with-developers-stephen-jones-nvidia) - [Shipping Faster with Less: Render on Cloud Hosting, AI Workloads, and the Future of DevOps](https://www.wearedevelopers.com/videos/1894-shipping-faster-with-less-render-on-cloud-hosting-ai-workloads-and-the-future-of-devops) - [Understanding Kubernetes in a visual way](https://www.wearedevelopers.com/videos/100085-understanding-kubernetes-in-a-visual-way) - [Efficient deployment and inference of GPU-accelerated LLMs​](https://www.wearedevelopers.com/videos/929-efficient-deployment-and-inference-of-gpu-accelerated-llms) - [Trends, Challenges and Best Practices for AI at the Edge](https://www.wearedevelopers.com/videos/630-trends-challenges-and-best-practices-for-ai-at-the-edge) ## Related Articles - [Dev Digest 120 - Apple and peers](https://www.wearedevelopers.com/magazine/455-dev-digest-120-apple-and-peers) - [Dev Digest 121 - AI goes offline](https://www.wearedevelopers.com/magazine/456-dev-digest-121-ai-goes-offline) - [Best US AI Conferences for CTOs in 2026: Build vs. Buy, Vendor Evaluation, and Peer Intelligence](https://www.wearedevelopers.com/magazine/736-best-us-ai-conferences-for-ctos-in-2026-build-vs-buy-vendor-evaluation-and-peer-intelligence) - [Dev Digest 132 - Binging WADFlix?](https://www.wearedevelopers.com/magazine/473-dev-digest-132-binging-wadflix) - [How We Built a Worry-Free System That Runs for 10+ Years – And What We’d Do Again](https://www.wearedevelopers.com/magazine/751-how-we-built-a-worry-free-system-that-runs-for-10-years-and-what-we-d-do-again) - [Highest Paying Tech Companies for Developers](https://www.wearedevelopers.com/magazine/220-highest-paying-tech-companies-for-developers)