Ph.D. Candidate
Manning College of Information and Computer Sciences
Amherst, Massachusetts, US
pboddavarama [at] cs [dot] umass [dot] edu
Ph.D. Candidate
Manning College of Information and Computer Sciences
Amherst, Massachusetts, US
pboddavarama [at] cs [dot] umass [dot] edu
(I'm on the job-market for industry post-docs and full-time research scientist positions! Please contact me if you think I would be a good fit for your team.) I'm a sixth-year Ph.D. student in Computer Science at the University of Massachusetts-Amherst. My research lies in the intersection of simulation and causal inference, in that I work on problems that adopt techniques from simulation for causal inference and causal inference for simulation. I construct interpretable, causal metamodels of discrete-event simulation systems and use simulation-based inference techniques to improve the evaluation of causal inference algorithms. I'm fortunate to be advised by Peter Haas and David Jensen.
I spent seven months (June 2023-Jan 2024) at X, the moonshot factory as an AI resident working on a project on plant biology. Previously, I spent a summer (Summer 2020) at EBSCO as a semantic and modeling intern working on information retrieval and extraction of metadata from clinical text for classification. I was also a Data Science for Common Good Fellow with the Center for Data Science in Summer 2019, where I worked on research involving disease modeling and risk assessment for communities in Massachusetts.
In a previous life, I worked at Cisco Systems (India) as a systems engineer. I was responsible for solution design and testing for routing, switching, wireless, and data center architectures. I also contributed to developing network programmability solutions for various technology. I have an undergraduate degree in electronics and telecommunication engineering.
Broadly, I aim to build explainable simulation metamodels using causal inference. I also work on improving evaluation of causal algorithms by developing new types of data that result in a more comprehensive and fair evaluation of estimators.