I am a Research Fellow in the AI4Code team at Microsoft Research. I am soon joining UC Berkeley as a PhD student to pursue my interests in Artificial Intelligence, Software Engineering, and Programming Languages. I am currently working on improving the code generation capabilities of Large Language Models (LLMs) and exploring how generative AI can automate software engineering tasks. My research focuses on improving the quality and correctness of code generated by Large Language Models (LLM) aiming to improve their reliability for software engineering and reasoning tasks. Most recently, I have been focusing on repository-level reasoning for code generation with LLMs. I have also explored long context usage, tool usage, better tokenization, prompting for code and decoding techniques with LLMs. Previously, I have worked in Programming Languages and Systems having developed language runtimes, IDE/Debugger support for languages, and source-to-source transpilers. Details of Past Work: Reliable code generation with LLMs: * Monitor-Guided Decoding (MGD): A novel technique (NeurIPS'23, 1st in Microsoft Global Hackathon) that prevents errors in LLM-generated code, even with smaller models. * multilspy: Open-source library simplifying LLM integration with language servers for static code analysis (like type completion). * PragmaticCode & DotPrompts: Benchmarks to test LLMs' real-world understanding of code on 10,000+ Java projects. Previously: Programming Languages and Systems: * Developed a runtime and IDE/debugger support for the CAL dataflow language as a Research Intern at VLSC Lab, EPFL. * Built Pytranslate, a transpiler converting Maxima code to Python (now part of Maxima). I'm excited to explore how generative AI can revolutionize software development. Connect with me to discuss the future of AI & code!