Description
Inworld is hiring a full-time backend or machine-learning systems engineer to build and optimize high-performance, scalable inference systems. The role focuses on serving frameworks such as vLLM or TRT-LLM, model acceleration, GPU profiling, distributed systems, Kubernetes, Ray, load balancing, and reliable production deployment. Candidates should have strong systems-programming experience, preferably a PhD or equivalent practical experience, and the ability to own models from research through production. The position offers a base salary of £140,000–£200,000 plus equity and benefits, requires legal right to work in the United Kingdom, and does not offer visa sponsorship.
