GitHub profile

Databricks Finance Forecasting Platform - AI-powered time series forecasting with MLflow and Unity Catalog

GUARD: Multi-Signal Hallucination Detection for RAG Systems

Audit protocol for testing conformal guardrails under distribution shift

DRIFTBENCH: Measuring Reliability Half-Life of RAG Systems Under Knowledge Drift

Production-oriented vector database benchmark framework with novel metrics: temporal drift, cost modeling, and operational complexity

End-to-end MLOps workshop on Databricks — learn how to train, track, register, and deploy ML models using PyTorch, MLflow, and Unity Catalog, with extensions to LLMOps via Mosaic AI.

Production-ready Databricks Asset Bundle for cross-region ML model serving using Delta Sharing. Deploy models and feature tables across workspaces with zero-copy data access and automated online fe…

Technical design documents for open source contributions

Databricks notebook demonstrating multi‑turn chatbot evaluation using MLflow GenAI. Includes sample dataset, rule‑based agent, guidelines and judges (e.g., Safety, Relevance), with optional evaluat…

this repo has code to develop various types of agents going from simple ReAct to Multi agent systems

Databricks example: train an XGBoost churn model, serve it with Model Serving, and query it from SQL using ai_query() for batch & interactive inference.

All the resources related to GenAI hands on workshop.

This repo contains code mentioned in the Understanding Pandas UDF in Apache Spark 3.0 article.

training-llms-from-scratch-private

This repo contains code for scaling BERT based entity resolution on Databricks for batch inference

all the code examples I use in my blogs