Isaac Rehg
Founding Engineer at Stealth Startup
San Francisco, California, United States
Summary
👤
Senior🎓
Top SchoolIsaac Rehg is a founding engineer based in San Francisco with eight years of experience specializing in ultra-low-latency LLM inference and production ML systems. At Cloudflare he led inference engine development for 50+ models, optimized GPU auto-scaling across 1000+ nodes, and applied techniques like KV cache compression and speculative decoding to improve throughput and costs. Now at a stealth startup he’s focused on delivering lightning-fast inference for next-generation AI applications, bringing same-day model deployment and image-generation preprocessing expertise. His background blends academic research in vision and translation from Georgia Tech and UC San Diego with practical consulting on object detection, giving him both theoretical depth and production chops. Notably, he has repeatedly moved research ideas into large-scale production constraints, balancing performance, pricing, and compatibility across rapidly evolving model releases.
8 years of coding experience
6 years of employment as a software developer
University of California, San DiegoMaster of Science - MS Computer Science, Master of Science - MS Computer Science at Georgia Institute of Technology
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (33)
inference10
to-do10
discord-bot10
cuda10
chatgpt9
pytorch9
amd9
python9
llm9
tpu9
llama9
mlops9
chat9
gpt9
transformer9
Programming languages (4)
Github contributions (5)
IsaacRe/tacklebox
Jan 2021 - Feb 2021
Contributions:36 commits, 9 pushes, 1 branch in 11 days
IsaacRe/vllm-kvcompress
Sep 2024 - Feb 2025
Contributions:47 pushes, 6 branches, 5 comments in 4 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.