Diwakar Mahajan

WORK HISTORY

EDUCATION

SKILLS

ABOUT DIWAKAR MAHAJAN

I’m a Senior Research Software Engineer at IBM Research in the Healthcare & Life Sciences group, where I design and build multimodal AI systems and LLM-based agents for accelerating drug discovery. My current work focuses on aligning structured biological data—such as molecular representations and protein sequences—with large language models to enable richer reasoning, retrieval, and decision support for biomedical researchers working on target screening and therapeutic design. Before focusing on drug discovery workflows, I worked extensively with Electronic Health Records (EHRs), tackling the full spectrum of clinical NLP problems—from question answering over EHR data and clinical summarization to large-scale benchmarking of domain-specific versus general-purpose language models. This included building clinical foundation models, evaluating their reasoning over longitudinal patient records, and leading multiple award-winning systems for clinical NLP challenges.Prior to joining IBM Research in 2016, I completed my Master of Science in Computer Science (with a focus on Natural Language Processing) at Columbia University in Fall 2015.