• Worked on multiple healthcare and life sciences projects including various types of Cancer, Atopic Dermatitis, and Metabolic Syndrome. Built and evaluated ML models on cancer datasets such as Lung Cancer (including CAR T-cell therapy and Squamous Cell Lung Cancer) and Metastatic Colorectal Cancer (mCRC). Developed models to predict Objective Response (Partial Response, Complete Response), Adverse Events (AEs), Serious Adverse Events (SAEs), Overall Survival (OS), and Progression-Free Survival (PFS). • Conducted research on the novel biomarker Serum Klotho for Metabolic Syndrome using longitudinal NHANES datasets spanning 2007–2023. Developed and evaluated multiple interpretable AI/ML classification models for Metabolic Syndrome risk prediction and simulated Klotho-serum modulation, contributing to a research poster accepted and presented at the International Society for Pharmacoeconomics and Outcomes Research/ISPOR—The Professional Society for Health Economics and Outcomes Research 2026 Conference at the Pennsylvania Convention Center, Philadelphia, USA. • Built machine learning models for LADA (Latent Autoimmune Diabetes in Adults), Type-1 (T1-D) & Type-2 (T2-D) diabetes prediction. • Collaborated with pharmaceutical and biotech clients including Johnson & Johnson (J&J), Bristol Myers Squibb (BMS), ADvantage Therapeutics Inc, Stratum Biosciences, and The University of Utah. • Led the design and development of enterprise-grade Generative AI solutions, building custom tools that streamlined business and research workflows. • Architected and deployed scalable traditional ML and AutoML solutions on AWS using SageMakerAI, Bedrock, Cloud9, ECR/Docker, and Elastic Beanstalk, optimizing for performance and cost efficiency. • Built a high-performance Retrieval-Augmented Generation (RAG) system using Mistral OCR, LangGraph, and ChromaDB, enabling processing of up to 2,000-page documents in under 60 seconds. • Optimized backend services and cloud infrastructure, reducing operational costs and saving the client over $24,000 (INR 2 million+).

Led the development of an AI Copilot ecosystem for a healthcare client, encompassing multiple cutting-edge functionalities: • Architected and deployed an AI Copilot for healthcare with information retrieval, data analysis, and a Clinical Trial Prediction Engine using Machine Learning. • Engineered a RAG (Retrieval-Augmented Generation) system with optimized vector database for enhanced information retrieval. • Integrated GenAI technologies like RAG & Vector Databases (FAISS, Pinecone), to enhance Copilot capabilities, improving clinical trial predictions by at least 30%. • Developed an intelligent Data Analysis Chatbot capable of handling complex quantitative queries and automated data visualization. • Created a Clinical Trial Prediction Engine using Machine Learning and Deep Learning techniques to forecast trial outcomes across various stages. • Implemented a Code Interpreter for automated programming assistance and data processing. • Also managed and mentored 2 interns during this period. Single-handedly architected and deployed end-to-end data and ML pipelines on AWS and GCP, managing all aspects from data preprocessing to model deployment. This comprehensive solution streamlined clinical trial analysis, improved prediction accuracy, and significantly enhanced data-driven decision making capabilities.

Worked on medical imaging data to discern and classify various objects, contributing to the development of accurate datasets for enhanced analysis and interpretation.

Solved problems related to core Computer Science Engineering subjects.

Development of the Depot Computerization System (DCS) Application and database upgradation. Responsibilities included working on Entity-Relationship (ER) diagrams to model, structure database entities, relationships and comprehensive exploration of database structures to ensure efficient data management and retrieval.