David Andrews is an undergraduate CS researcher at Georgia Tech focused on building LLM agents that perform economically meaningful, long-horizon work across software and hardware domains. He trains agents with RL for reasoning and tool use, applies them to automated bug finding in LLVM, and benchmarks agent performance on real-world Verilog/RTL hardware design tasks. As an organizer at DuckAI he shipped DuckTrack for multimodal agent training data and contributed to open-source replicates of AlphaEvolve, demonstrating a knack for practical systems and reproducible research. With nine years of programming experience spanning compilers, digital logic, and ML, he’s graduating May 2026 and actively pursuing PhD programs or research roles that push agent capability and continual learning.
9 years of coding experience
Bachelor of Science - BS, Computer Science, Bachelor of Science - BS, Computer Science at Georgia Institute of Technology
An application to manage tenant information and track visitor sign in/out logs
Contributions:47 commits, 12 PRs, 30 pushes in 5 months
ltssign-intenantsignvisitor
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.
Request Free Trial
David Andrews - Undergraduate Researcher, Chao Zhang Lab