Architected and deployed a production-grade agentic RAG application.

Reduced support query resolution time through intelligent document retrieval.

Containerized with Docker using uv for Python dependency management and deployed to Google Cloud Run with CI/CD via Cloud Build.

Built a model to analyze discovery logs and focus on new alerts via clustering, reducing human time for triage and providing error log insights using in-house LLM models.

Developed an agentic AI-powered alert management system to streamline SRE workflows and designed an LLM-based architecture with a RAG pipeline grounded in a domain-specific knowledge graph.

Built a model to accurately estimate workflow runtimes for ServiceNow customers, enabling better planning and prioritization, and implemented CI/CD pipelines for seamless deployment following MLOps best practices.

Built and deployed a robust ML pipeline on Databricks that generates personalized recommendations.

Developed a user-friendly tool using Streamlit for clients to visualize product recommendations.

Analyzed out-of-stock revenue data to highlight missed opportunities.

Worked on luis bot framework to develop a multiple virtual assistants on a single chatbot for a client.

Developed a chatbot for a hospital help desk using RASA.

Modified clinicalBERT according to the requirement.

Developed ML models to analyze IT ticket conversations and server data, including sentiment analysis, keyword detection, and anomaly detection.

Implemented scalable experiment tracking and data processing platforms by deploying MLFlow.

Established a standalone Spark architecture, diskover application to scrape filesystem metadata.