51 to 58 of 58 vLLM Jobs in London

improve throughput and cost per token, partnering with the CUDA/GPU engineersMake the core software architecture calls on serving frameworks and orchestration (e.g. vLLM, TensorRT-LLM, SGLang, Triton Inference Server or equivalents)Translate throughput, latency and uptime commitments into concrete technical specifications and serving capacity plansAct as direct technical ...

throughput and cost per token, partnering with the CUDA/GPU engineers. Make the core software architecture calls on serving frameworks and orchestration (e.g. vLLM, TensorRT-LLM, SGLang, Triton Inference Server, or equivalents). Translate throughput, latency, and uptime commitments into concrete technical specifications and serving capacity plans. ...

optimized in a Data Center AI software platforms Inference, model deployment, runtimes, SDKs, developer tools. AI orchestration frameworks, e.g., Kubernetes-based systems, Ray, vLLM, TGI. Cloud-native AI software stacks, deployment patterns, and data center operating models. Data center AI infrastructure CPUs, GPUs, NPUs, and heterogeneous accelerator environments. Kubernetes-based ...

generation Depth in multi‐agent systems, planning, program synthesis, or retrieval over structured artefacts such as codebases Deep familiarity with the internals of SGLang, vLLM, or comparable inference serving frameworks - scheduler design, memory management, and execution pipelines A background in another field that studies systems of interacting heterogeneous components - neuroscience ...

results focus. What you will do: Operate the LLM estate: run LoRA fine-tuning cycles and evaluation gates on our GPU hardware, manage vLLM serving (including multi-adapter deployments) alongside production, promote or roll back model versions on the gate results, and keep the serving watchdogs healthy. The CEO retains … world system of record. Python for scripting, data processing or pipeline work. Preferable: Deeper LLM experience: fine-tuning methodology, corpus design, evaluation-harness construction, vLLM internals, or heavy daily use of AI coding agents. ERP, FSM or works-management domain experience job lifecycles, scheduling, SLAs, parts, timesheets, invoicing or heat ...

backed challenger lab building state-of-the-art computer-use agents. The inference team owns the full stack from engine layer (vLLM, SGLang) through to serving architecture (disaggregated inference, intelligent routing). The team operates at the intersection of research and production - translating cutting-edge techniques directly into the systems … least one systems language - Rust, C++, or Go Hands-on experience with PyTorch or JAX in an industry setting Experience with inference frameworks: vLLM, SGLang, TensorRT-LLM Solid distributed systems fundamentals and experience operating production ML infrastructure Working knowledge of modern ML including transformers and multimodal architectures Optional Bonus Research ...

implementation level. Attention variants, KV cache strategies, quantisation schemes, and how they shape kernel design You've worked with production inference or training frameworks, vLLM, Megatron-LM, etc You've built performance-critical infrastructure before - compilers, profilers, auto-tuners, or search systems You have real intuition for evolutionary methods, fitness … work of François Chollet, Kenneth Stanley, Jeff Clune, Jurgen Schmidhuber, David Ha, and Christian Szegedy Bonus: Open-source kernel contributions (FlashAttention, FlashInfer, vLLM, Unsloth, Liger-Kernels, ThunderKittens) Publications in ML/AI, kernel optimisation or evolutionary methods (NeurIPS, ICLR, CVPR, GECCO or equivalent) Other HW experience (AMD, MLX, edge ...

direction you shape across the platform. Responsibilities Own the Runtime & Serving Stack: Design, build, and extend the distributed inference and serving stack (e.g. vLLM, SGLang, NVIDIA Dynamo, TensorRT-LLM) onto DX-1, rather than treating any layer as a black box. Scale Distributed Inference: Define how inference scales across many … runtime/network/accelerator boundary. Demonstrated ownership of a hard, end-to-end systems problem, ideally extending a distributed inference/serving stack (vLLM, SGLang, NVIDIA Dynamo, TensorRT-LLM) in production, with specifics on what you built or changed and why. Distributed inference at scale: parallelism strategies, collective communication ...