Summary
Nihar Sanda is a Machine Learning Engineer based in Boston with six years of hands-on experience building production-grade systems that blend knowledge graphs, computer vision, NLP, and multimodal models. At Northeastern’s Institute for Experiential AI he led development of PRISM and the novel eGoT algorithm, delivering state-of-the-art multi-hop reasoning and outperforming competing GraphRAG methods in biomedical settings. He has a track record of engineering scalable real-time inference on Kubernetes, privacy-preserving federated learning, and affect-recognition pipelines deployed across academic and classroom environments. Equally comfortable with research and production, his master’s thesis and publications demonstrate end-to-end systems combining Neo4j, GPT-family transformers, and vector search to process millions of documents and relations. He also brings startup and open-source experience—from co-founding a multi-tenant SaaS backend to mentoring and contributing to PEcAn and CERN-related projects—making him adept at translating cutting-edge research into practical impact.
6 years of coding experience
4 years of employment as a software developer
SSC, SSC at Don Bosco High School - India
Bachelor of Technology - BTech, Computer Science, Bachelor of Technology - BTech, Computer Science at Indian Institute of Information Technology Dharwad
HSC, PCM, HSC, PCM at Pace Junior Science College
Master of Science - MS, Computer Science, Master of Science - MS, Computer Science at Khoury College of Computer Sciences