Michael Feil
SVP, Shipping Department at Baseten
San Francisco, California, United States
Summary
🤩
Rockstar🎓
Top SchoolMichael Feil is an engineering leader focused on high-performance ML infrastructure and production-grade serving systems, currently SVP of Shipping at Baseten where he builds distributed LLM inference stacks and embeddings runtimes. With an M.Sc. in Robotics from TU Munich and six years of experience across research and industry, he bridges deep learning research (1M+ context-length causal LM training) with engineering pragmatism in Rust/TypeScript/Python. He maintains Infinity, an open-source low-latency serving engine used in production by companies like Runpod, SAP, and Hugging Face, and has optimized kernels for Hopper/Blackwell GPUs. Michael combines hands-on optimization (flash-attn and weights-caching libraries) with product-oriented shipping, and prefers DM contact via Twitter or email rather than job-seeking channels.
6 years of coding experience
5 years of employment as a software developer
Bachelor's degree, Mechatronics and Information Technology, Bachelor's degree, Mechatronics and Information Technology at Karlsruhe Institute of Technology (KIT)Master of Science - MS, Robotics, Cognition, Intelligence, 1.5 (with distinction), Master of Science - MS, Robotics, Cognition, Intelligence, 1.5 (with distinction) at Technical University of MunichTechnical University of Denmark
German, English, French, Spanish
Github Skills (200)
language-model10
sentence10
code-generation10
quantization10
spotify10
serve10
intel10
llmops10
xpu10
evaluation-framework10
nlp10
haystack10
text-generation10
sentence-embeddings10
data-science10
Programming languages (18)
Github contributions (5)
michaelfeil/infinity
Oct 2023 - Mar 2025
Infinity is a high-throughput, low-latency serving engine for text-embeddings, reranking models, clip, clap and colpali
Contributions:88 releases, 87 reviews, 376 PRs in 1 year 5 months
bert-embeddingsllmtext-embeddings
michaelfeil/iot_gateway_modbus
Apr 2020 - Aug 2022
A MQTT Gateway connecting Modbus RTU and Google IoT Core
Contributions:3 PRs, 12 pushes, 2 branches in 2 years 3 months
rtugoogle-iot-coremodbusraspberry-piopcua
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.