About Me: I'm a research scientist at OpenAI, teaching future AI understand and explore science. 

​

Before joining OpenAI, I completed my PhD at the University of Edinburgh, where I focused on language models for better compiler optimizations and more robust runtime program analysis. During my PhD, I had the luck to work with the best three advisors I could ever wish for: Ajitha Rajan, Hugh Leather and Pavlos Petoumenos. See my thesis here.

​

Aside from my PhD, I have worked on a few interesting projects in the field of machine learning, compiler engineering, or both combined.

​

In 2023, I was a part-time research scientist at Tik-Tok, where I worked on fault localization of concurrency execution bugs in GO routines using LLMs. In 2022, I was a research intern at FAIR - Meta AI. My research work involved PPO/TRPO RL-based LLMs for OpenCL/CUDA kernel synthesis. In 2019, I worked at ARM as a software engineering intern where I shipped Armv8 GICv4's distributed multichip operation for ARM-based distributed servers. In 2021, I was hired as a ML research lead by a Greek startup to design and implement a real-time recommendation system for art exhibitions!