Charles Harris is a software engineer with 7 years' experience, currently working at Graphcore and contributing as an ML engineer at Hugging Face on the side. He combines strong back-end systems skills with applied ML infrastructure experience, having improved vLLM's API server security (adding SSL), benchmark integrations for OpenAI-compatible serving, and migrated observability metrics to prometheus_client. A Bristol-based dual-degree engineer with a Distinction MSc in Computer Science and a first-class BEng in Aerospace-aligned engineering, he brings rigorous academic grounding to production-grade inference tooling. His internships at CFMS and hands-on work on high-throughput LLM serving show a practical focus on scalable, secure model deployment.
7 years of coding experience
1 year of employment as a software developer
Master of Science - MS, Computer Science, Distinction, Master of Science - MS, Computer Science, Distinction at University of Bristol
A high-throughput and memory-efficient inference and serving engine for LLMs
Role in this project:
Back-end Developer
Contributions:179 reviews, 243 PRs, 12 pushes in 1 year 3 months
Contributions summary:Charles made several contributions focused on enhancing the API server functionality of the vLLM project. This included adding SSL support to the API servers for secure communication and modifying the benchmark serving script to support the OpenAI API server. Furthermore, the user refactored and updated the benchmark serving script, enhancing the integration with the server's HTTPS protocol. The user also ported metrics from `aioprometheus` to `prometheus_client`.
Contributions:16 releases, 1 review, 57 commits in 2 years 4 months
reacthostauction-websitejavascriptauction
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.