- 🚀 I've been working on AI for code (née ML4Code) since 2012. I research and engineer AI systems to make developing and maintaining software productive, enjoyable, and less error-prone.
- 🤝 As of June 2026, I am at Apple. Previously I was a staff research scientist at Google DeepMind and a principal researcher at Microsoft Research.
- 👉 I enjoy building AI, practical developer tools, training and orchestrating agentic systems, and solving real-world problems with machine learning and optimization methods.
🤖 LLMs & Agentic Systems
- 📊 Evaluation of LLMs and agentic systems
- 🕵 Agentic systems for cybersecurity
- 🏋 Post-training: RL for software engineering tasks
- ⚡ Architecture of ML Models
💻 AI for Software Engineering
- 🔎 Automated bug detection and program analysis
- ⌨ Code generation, synthesis, and analysis
- 🦾 AI–human collaboration in software engineering
- 🔨 Practical developer tools
- 🔗 The interplay of formal, sound analyses with LLMs and agents
🔥 Highlighted Publications (👉 Full list)
As the industry has moved away from publishing, I have also ceased to work/submit academic publications.
