About this role
Senior Software Engineer (vLLM) at CommonAI C.I.C.. Location: Cambridge, England, United Kingdom. Role: deploying models, optimizing inference, upstreaming code Requirements: Deep expertise in Python and low-level programming (C/C++, Rust, assembly, CUDA); experience contributing to vLLM or similar ML/AI open-source projects; understanding of LLM inference and accelerator performance optimisation. Category: Software Development Seniority: Senior Level Tools: vLLM, Python, C, C++, Rust, assembly, CUDA, PyTorch, Hugging Face TGI, TensorRT-LLM, Ray, GPUs, TPUs, CPU vector units Commitment: Full Time Workplace: Onsite Languages: English