Erik Kaunismäki
Software Engineer at Hugging Face
Paris, Ile-de-France
Summary
🤩
Rockstar🎓
Top SchoolErik Kaunismäki is a software engineer based in Paris with 4 years of experience building infra and AI inference systems, currently working on infra and inference at Hugging Face. He thrives at the intersection of systems and ML—shipping backend and DevOps improvements for high-profile projects like Hugging Face’s text-generation-inference, including cache fixes, usage metrics, API key auth, and GPU/XPU monitoring. Comfortable pushing technical limits, he builds custom tooling and experiments with running LLMs in WASM, virtual machines, and serverless ML platforms. His primary languages are Rust, Python and JS/TS, with prior Go experience and a curiosity-driven plan to explore Gleam. Pragmatic about simplicity, he balances deep technical tinkering with a user-focused mindset and a reputation for fostering positive, collaborative teams. A former platoon leader and student union vice-chair, he brings disciplined leadership and clear communication to complex engineering problems.
4 years of coding experience
4 years of employment as a software developer
Master of Science - MS, Economics, GPA: 4/5, Master of Science - MS, Economics, GPA: 4/5 at Hanken School of EconomicsMatriculation Examination, Upper secondary school, Eximia cum laude approbatur, Matriculation Examination, Upper secondary school, Eximia cum laude approbatur at Gymnasiet LärkanBachelor of Science - BS, Economics, Bachelor of Science - BS, Economics at University of Amsterdam Business School
Swedish, Finnish, English, French, German
Github Skills (12)
rust10
inference10
api10
apidoc10
dockers9
system-monitoring9
telemetry9
docker9
error-handling8
devops8
pytorch7
transformer7
Programming languages (8)
Github contributions (5)
huggingface/text-generation-inference
Jul 2024 - Mar 2025
Large Language Model Text Generation Inference
Role in this project:
Backend Engineer & DevOps Engineer
Backend Engineer & DevOps EngineerContributions:36 reviews, 29 PRs, 64 pushes in 8 months
Contributions summary:Erik primarily contributed to the backend infrastructure and configuration of the text generation inference system. Their work includes fixing cache directory handling, implementing usage statistics collection, and adding authorization via API keys. Furthermore, the user worked on integrating NVIDIA SMI information, xpu-smi info, and crash report mechanisms, demonstrating experience with system-level monitoring and debugging within the project.
nlppytorchlanguage-modelbloombert
ErikKaum/demo
Apr 2023 - Jan 2024
Contributions:5 PRs, 54 pushes, 4 branches in 9 months
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.