About Me

Benjamin Mikek is a Ph.D. candidate in the School of Computer Science at Georgia Tech, advised by Professor Qirun Zhang. My work lies at the intersection of compilers, formal verification, and agentic AI: I study how to make programs, whether written by humans or LLMs, correct and performant. My work has appeared in top-tier programming-languages conferences, including PLDI and OOPSLA, and won a distinguished paper award at FSE. I have extended my experience with two industry internships at AWS in 2025 and 2026.

Research areas A Venn diagram of three areas that meet at a small central region: Compilers, Formal Verification, and Agentic AI. A dot marks the small region where all three overlap. Compilers FormalVerification AgenticAI

Publications

News

  • August 2026 I will present a poster on using the OEIS for compiler optimization at the 2026 LLVM Developers’ Meeting in Santa Clara.
  • August 2026 My paper Spatial and Temporal Decomposition for Faster Translation Validation will appear at OOPSLA 2026.
  • April 2026 I will return to AWS to work on verified agentic code generation in summer 2026.
  • January 2026 I will be a rapid artifact reviewer for PLDI 2026.
  • December 2025 I have been admitted to candidacy after defending my dissertation proposal.
Older news
  • August 2025 I will present at the SPLASH 2025 Doctoral Symposium in Singapore.
  • February 2025 I will be joining AWS as an applied scientist intern in summer 2025.
  • January 2025 I will be a member of the artifact evaluation committee for PLDI 2025.
  • March 2024 My paper, SMT Theory Arbitrage: Approximating Unbounded Constraints using Bounded Theories, will appear at PLDI 2024.
  • February 2024 I will present my work on leveraging LLVM optimizations for constraint solving at EuroLLVM 2024 in Vienna on 10 April.
  • January 2024 I will be a member of the artifact evaluation committee for PLDI 2024.
  • January 2024 I will be a member of the artifact evaluation committee for CAV 2024.
  • December 2023 My paper, Speeding up SMT Solving via Compiler Optimization, won an ACM SIGSOFT Distinguished Paper Award at FSE 2023.