CV
Professional summary
I lead applied AI work from research framing and architecture through evaluation and enterprise delivery. My experience spans agentic systems and retrieval, multimodal and multilingual models, and document AI. I have built and grown applied-science teams from inception through architecture and delivery of enterprise semantic layers, personalized search and agents, and support automation. A recurring focus is making evaluation useful for product decisions and building capabilities that multiple teams can reuse.
Current role and experience
Current title: Senior Principal Applied Scientist, Generative AI, Oracle Cloud Infrastructure (OCI).
Company tenure: Oracle Cloud Infrastructure, April 2021–present.
My work spans shared knowledge and retrieval systems, agentic applications, multimodal and multilingual search, and evaluation. Earlier roles include Data Science Lead, Computer Vision at Jio Platforms and Data Scientist at Abzooba Infotech.
Selected contributions
- Owned applied-science contributions to multimodal and agentic enablement of Oracle Fusion ERP and Oracle AI Database 26ai, including multimodal RAG, embedding fusion, image understanding, and text-to-image capabilities with product engineering.
- Develop support agents for cloud-console assistance, ticket triage, and DevOps incident resolution; architect Agent Hub routing, skill/tool retrieval, and shared context and memory for long-horizon tasks.
- Developed a personalized leadership-coaching agent pilot combining assessment-driven plans, persistent memory, retrieval-grounded recommendations, role-play practice, and proactive nudges.
- Led a multi-agent platform across 15+ engagements and delivered document-understanding capabilities to 20+ customers.
- Lead workshop organizer for GRAIL-V at CVPR, SURGeLLM at ACL, and DocInsights at EMNLP.
- Inventor on 10 issued patents, with 41 pending (author-reported count, October 2026). The patent collection links selected public records.
Research areas
- Retrieval, ranking, and agentic systems
- Multimodal and multilingual models
- Evaluation, robustness, and responsible AI
- Document AI and synthetic data
Education
- MS, Machine Learning & Artificial Intelligence, Distinction — Liverpool John Moores University
- BTech, Computer Science & Engineering — Institute of Engineering & Management (IEM), West Bengal University of Technology
Resume
If the preview doesn’t load, use the download link above.