Senior / Principal Machine Learning Engineer – UK

Inworld AI conducts advanced research in realtime voice models used across various AI applications, powering millions of end users globally. The role involves developing and optimising high-performance machine learning models, working with cutting-edge frameworks like vLLM and TRT-LLM. Candidates will manage full-cycle model deployment, ensure system scalability, and contribute to open-source inference engines. Expertise in C++, CUDA, Python, or Rust, and experience with Kubernetes or Ray, are essential for performance tuning and distributed inference. A background in computer science, physics, or mathematics with practical backend or ML system development is required. The role demands innovative problem-solving, a bias for impact, and a keen interest in pushing AI capabilities forward.