William Zeng is a software engineer and entrepreneur with seven years of experience building AI-driven developer tools and search systems. He co-founded Sweep (YC S23), shipping one of the earliest coding agents and a JetBrains-focused AI assistant, and led backend work on code analysis and retrieval features like search_snippets. Before Sweep he advanced quickly at Roblox—rewriting the game search indexing pipeline, mentoring interns, and delivering a measurable 10% lift in search quality as a Senior ML Engineer. Currently a Member of Technical Staff at xAI in San Francisco, he blends machine learning and backend engineering to ship production-grade AI products. A Carnegie Mellon-trained statistician/ML practitioner, he pairs rigorous quantitative thinking with hands-on system design. Notably, his open-source contributions on Sweep reveal a focus on the internal tooling that powers reliable code assistance for developers.
7 years of coding experience
5 years of employment as a software developer
Bachelor's degree, Statistics/Machine Learning, Bachelor's degree, Statistics/Machine Learning at Carnegie Mellon University
Contributions:1 release, 781 reviews, 759 PRs in 1 year 9 months
Contributions summary:William primarily worked on backend-related tasks, indicated by the changes in `sweepai/core/sweep_bot.py`, `sweepai/agents/graph_child.py`, and `sweepai/utils/search_utils.py`. The commits involve modifications to code assistant tools, suggesting a focus on the internal workings of code analysis and retrieval. The changes incorporate features such as integrating a new function, `search_snippets` and improved code.
Contributions:58 reviews, 57 PRs, 72 pushes in 1 year 1 month
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.