2 of 2 Hugging Face Jobs in the East of England

MLOps: Champion code quality, reproducibility, automation (CI/CD), observability and evaluation, with production deployment to cloud/HPC using Python, PyTorch, JAX, Hugging Face, MLflow, vLLM, Docker, and Kubernetes; employ agent frameworks such as LangGraph, OpenAI Agents SDK, Microsoft Agent Framework and Google ADK; use interoperability standards ...

Rust, assembly or CUDA). A history of direct contributions to vLLM or similar high-performance open-source ML/AI projects (e.g. PyTorch, Hugging Face TGI, TensorRT-LLM, Ray). Strong understanding of LLM inference mechanics (e.g. KV caching, continuous batching, memory management, model quantisation). Experience ...