Software Engineer / Ai Contributor
AfterQuery Experts
Sep 2025 - Current (11 months)
• Contributed to Harbor and Terminal Bench, internal tooling products powering AfterQuery's AI evaluation infrastructure.
• Played a key role in building and launching IDE-Bench (ide-bench.com), a public multi-language benchmark for evaluating AI agents on real-world software engineering tasks — a major milestone for the team.
• Worked on Project Puzzle, contributing to benchmark design, evaluation pipelines, and data quality processes that underpin IDE-Bench's leaderboard and trajectory analysis.
• Collaborated with a distributed team to ensure benchmark integrity, reproducibility, and coverage across multiple programming languages and IDE environments.