Dan Gilles

Resume

Dan Gilles

AI engineer · Agent infrastructure · Developer tools

Summary

AI-native full-stack engineer who builds directly with the people who use the software. I build agent infrastructure, including Eyrie and Commander, and contribute as a code owner to ZeroClaw. Coding agents write much of my code. I specify the problem, review every change, test it live, and decide what ships.

750+ merged pull requests

Experience

  1. Apr 2025 to Oct 2026

    AI Engineer, Contract

    Superbuilders

    Built full-stack pilots and agentic workflows directly with curriculum and product teams. Turned needs into requirements and explained cost, reliability, and readiness tradeoffs. These projects were demoed or piloted, not shipped to production.

    • Civics Debate Academy: co-wrote the PRD and built the full-stack app with AI judging and real-time multiplayer, in partnership with the Bill of Rights Institute. Demoed to Bill of Rights Institute leadership, then piloted in classrooms with 39 students.
    • Flying Colors: a team-built civics app. Produced the cinematic lesson videos with AI video generation and brought the Bill of Rights Institute in for a demo. Piloted with middle-school students.
    • Civics Time Machine, later Witness: solo builder and video producer for a video-first history app. Built an AI video pipeline that retries defective clips before human review. Demoed to stakeholders.

    Partner: Bill of Rights Institute

  2. Mar 2026 to present

    Code Owner and Core Contributor

    ZeroClaw

    Contribute to an open-source Rust agent runtime, with code ownership across runtime, tools, gateway, configuration, memory, and cost code.

    • Fixed mid-turn steering delivery and a race that silently dropped late steering messages.
    • Traced prompt-cache misses to three causes, with one fix per cause. A controlled A/B on the same 30 prompts raised cache hit rate from 81.8% to 93.1% and cut effective input cost about 51%.

  3. Dec 2024 to Mar 2025

    Software Engineering Fellow

    Gauntlet AI, Cohort 1

    Completed a 12-week, 1,000-hour AI-first program, building a new application from scratch every week.

  4. Nov 2023 to May 2024

    Graduate Student Researcher

    University of Chicago Knowledge Lab

    Created technical visualizations of neural networks and training dynamics for a forthcoming deep learning textbook.

  5. 2012 to 2021

    English and STEM Educator

    Beijing

    Taught English and STEM, and worked as a Chinese-English translator and editor.

Skills

Languages and frameworks
TypeScript, React, Vite, Node.js, Go, Rust (Tokio), Python, SQL
Data and real-time systems
PostgreSQL, SQLite, Socket.io, SSE
AI engineering
LLM provider integration, tool calling, streaming fallback, prompt caching and cost analysis, evals
Development tools
Git, Claude Code, Codex, Cursor

Education

University of Chicago
M.A., Computational Social Science (NLP/ML) · 2024
St. John's College, Santa Fe
M.A., Eastern Classics · 2022
St. John's College
B.A., Liberal Arts (Great Books) · 2013

Languages

English, native. Mandarin Chinese, professionally fluent.