Hi! I'm Raja...

I am a Research Fellow in the AI-Infrastructure team at Microsoft Research India, where I work on optimizing systems for efficient inference of Large Language Models (LLMs). Currently, I am exploring ways to enable determinism in LLM inference efficiently. In 2023, I graduated from the Undergraduate Programmes at IIT Bombay, where I earned my B.Tech (with Honors) in Computer Science.

My research interests broadly lie in computer systems, with a current focus on making them more efficient for modern machine learning workloads.

When deadlines are quiet and time slows, you may find me taking infinite walks or sitting somewhere with a book. I used to weave my thoughts into words (check out the poetry below!), though I have stopped doing that recently.

• Poetry
• Notes

Research

Service