About Me

I’m a second-year PhD student in the Data Systems Group (DSG) at MIT where I am advised by Tim Kraska.

My early PhD work has explored applying techniques from declarative optimization to novel AI systems. We recently published a vision paper in CIDR’25 for our prototype system called Palimpzest (PZ), which enables users to compose AI systems out of semantic operators. PZ’s optimizer can then optimize these systems for a given objective across the dimensions of quality, cost, and runtime.

Following-up on our vision paper, we are currently exploring a few different research directions

• We would like to make our optimizer more robust and principled, borrowing and adapting ideas from traditional Database query optimizers
• We are investigating how to apply optimization techniques to AI systems which are (A) not declarative in nature, but (B) still make use of semantic operators
• We are interested in making our optimizer more adaptive, so that it can propose new plans on a per-input basis
• In another vein of exploration, we are working a project to assist with software development for large-scale systems over long time horizons (i.e., not just synthesizing a small function, class, or commit).

Before coming to MIT, I worked at Cambridge Mobile Telematics (CMT) while also pursuing a Master’s degree at Stanford under the wonderful guidance of Daniel Kang and Matei Zaharia.