Manish Nagireddy

I am a Research Software Engineer at IBM Research and the MIT-IBM Watson AI Lab. My main research goal is to build trustworthy AI solutions. My research interests encompass several areas in machine learning and artificial intelligence from classical ML methods to natural language processing and the generative context. My current work focuses on use-case centered algorithmic auditing and evaluation, in the context of large language models. I am a core maintainer for many open-source trustworthy AI toolkits - AI Fairness 360, AI Explainability 360, and Uncertainty Quantification 360.

Before joining IBM Research, I graduated from Carnegie Mellon University with a B.S. in statistics, machine learning, and computer science.