AI/ML Engineer with 3+ years of experience specializing in Generative AI and production-ready MLOps. With a background in HealthTech and a peer-reviewed publication, my mission is to leverage cutting-edge AI to build scalable, reliable systems that solve real-world problems. I thrive on the challenges of moving complex models from prototype to production, with a focus on mitigating hallucination and ensuring robust, test-driven development.
- Leveraging Community Health Workers for Unsupervised Readmission Prediction – International Journal of Semantic Computing, Vol. 18, No. 01, April 2024
| Project | Description | Key Technologies |
|---|---|---|
| scholar-agent | An advanced multi-agent research assistant using LangGraph, a Knowledge Graph (Neo4j), and a re-ranking RAG pipeline to reason over scientific papers. | LangGraph, Google Gemini, Neo4j, ChromaDB, sentence-transformers, rich |
| vertex-care | Operationalized my peer-reviewed, published research on patient readmission by building an agentic MLOps platform to generate actionable intervention plans for high-risk patients. | Published Research, LLM Feature Extraction, Google Gemini, ReAct Agent, FastAPI, MLOps |
| claim-triage-ai | Operationalized an intelligent claim triage pipeline that predicts denials, clusters root causes via NLP, and routes high-priority claims for automated processing. | XGBoost, Sentence-BERT, Clustering, FastAPI, Streamlit, Docker, CI/CD |
| nutri-serve-ai | A personalized AI nutrition expert powered by RAG and Google Gemini, wrapped in a FastAPI/Gradio UI and deployed with a full CI/CD pipeline. | RAG, Google Gemini, FastAPI, Gradio, CI/CD |
| ish-vaani | An NLP toolkit for Hindi/Hinglish, focused on analyzing custom tokenizers and building interactive tools for model interpretability, robustness, and AI safety. | Custom Tokenization, Interpretability, AI Safety, TransformerLens, LoRA, Hugging Face |
