Sankar Mukherjee
Data | AI | Data Infrastructure Engineering
About Me
I’m a Data & AI Engineer with a strong foundation in Big Data and Data Engineering, now specializing in building AI-powered systems and LLM-driven applications. In past also worked on the field of Data Infrastructure Development.
My journey started in large-scale data ecosystems—designing and optimizing data pipelines, working with distributed systems, and enabling reliable data platforms. Over time, I transitioned into AI Engineering, where I focus on building intelligent systems powered by Large Language Models (LLMs) and modern agent frameworks.
I enjoy bridging the gap between data infrastructure and AI applications - ensuring models are not just innovative, but scalable, production-ready, and business-impacting.
Bio
Professional Skills
Work Experience
Education
Work Profile
Development / Data / Warehouse | Data Lake | Big Data | ETL
Modern Data Pipeline
Design, Built highly flexible, scalable, fault tolerent Data Warehouse, Data Lake, Data pipeline.
Development / AI / LLM Driven Applications
Big Data Lake
Design, Build Agentic Systems, Workflow Orchestration with LLMs, Retrieval-Augmented Generation (RAG), and scalable AI architectures.
Certifications
Development / Data / Big Data
Databricks Certified Associate Developer for Apache Spark 3.0
October 2022
Development / Language / Java
Java Standard Edition 6 Programmer Certified Professional
November 2011








