Generative AI Engineer and Data Engineering professional with 5+ years of experience building scalable ETL/ELT pipelines, enterprise data warehouses, cloud data platforms, and enterprise analytics solutions, with recent specialization in LLM-powered applications and AI data pipelines.
Certified Generative AI Engineer through Databricks Generative AI Engineer Associate, with knowledge of building LLM pipelines, Retrieval-Augmented Generation (RAG) systems, and AI applications on the Azure Databricks Lakehouse platform.
Practical knowledge of designing LLM-powered workflows using frameworks such as LangChain, enabling integration of Large Language Models (LLMs), vector search, and enterprise data sources to build intelligent assistants and AI-driven analytics tools.
Strong understanding of LLM architecture and prompt engineering techniques, including prompt optimization, chain-of-thought prompting, few-shot prompting, and prompt templates to improve AI response quality and reliability.
Knowledge of implementing Retrieval-Augmented Generation (RAG) architectures, combining vector databases, embeddings, and document retrieval pipelines to enable LLMs to generate accurate responses using enterprise knowledge bases.
Familiar with vector database technologies used in AI applications, including FAISS, Pinecone, and Chroma, supporting semantic search, embeddings storage, and knowledge retrieval for LLM systems.
Hands-on practice designing end-to-end LLM pipelines for enterprise AI applications, including data ingestion, embedding generation, vector indexing, retrieval pipelines, prompt orchestration, and response generation workflows.
Skilled in building and optimizing data pipelines using Informatica PowerCenter and IICS, integrating enterprise data sources such as RDBMS, flat files, XML, mainframes, and Salesforce into modern cloud warehouses including Snowflake and Amazon Redshift.
Self-Practice in implementing modern data Lakehouse architectures using Medallion Architecture (Bronze, Silver, Gold layers) to organize raw, refined, and curated datasets for analytics, machine learning, and AI workloads within scalable data platforms.
Strong expertise in data modeling and enterprise data warehousing, designing fact and dimension tables, Type II SCD implementations, and star/snowflake schemas supporting claims analytics, policy systems, and customer insights.
Completed AI Business Strategies & Applications certification from University of California, Berkeley, gaining knowledge in AI solution architecture, experimentation frameworks, and identifying high-impact AI use cases within enterprise systems.
Developed an AI-powered coffee demand prediction model using Python and machine learning, improving forecast accuracy from 60% to 90% through integration of external datasets such as weather and events, demonstrating the ability to combine data engineering, predictive analytics, and experimentation frameworks.
Experience working with cloud ecosystems including Amazon Web Services and Microsoft Azure, with knowledge of cloud deployment models (IaaS, PaaS, SaaS), data security, governance, and scalable analytics architectures.
Passionate about modernizing traditional BI and ETL platforms with Generative AI capabilities, including AI assistants for analytics, LLM-powered knowledge retrieval, intelligent automation, and AI-driven decision support systems.
Additional Certifications: Snowflake Data Warehousing Professional Badge, Microsoft Azure Fundamentals, IBM Certified Data Scientist, multiple Coursera Data Science/ Python courses demonstrating a strong commitment to continuous learning and modern cloud data practices.
Overview
5
5
years of professional experience
1
1
Certification
Work History
Informatica Developer
Accenture Services Pvt. Ltd
01.2014 - 01.2019
Worked as an Application Development Analyst in Accenture Services Pvt. Ltd, from 2014 – 2019
Education
Bachelors of Technology(B.Tech) -
Jawaharlal Nehru Technological University (JNTUH)
Hyderabad, India
01-2014
Skills
Generative AI & LLM Technologies: AI Application Development, Embeddings & Semantic Search, LangChain Framework, Large Language Models (LLMs), Prompt Engineering (Few-shot, Chain-of-thought, Prompt Templates), Retrieval-Augmented Generation (RAG), Vector Databases (FAISS, Pinecone, Chroma)
Data Engineering & Data Platforms: Data Modeling (Star Schema, Snowflake Schema), Data Warehousing & Analytics Platforms, ETL/ ELT Pipeline Development, Informatica Intelligent Cloud Services (IICS), Informatica PowerCenter, Slowly Changing Dimensions (Type II SCD)
Cloud & Data Architecture: Amazon Redshift, AWS Cloud Services, Cloud Data Architecture, Databricks Lakehouse Platform, Microsoft Azure, Snowflake
Operating Tools: Linux, Unix, Windows
Scripting language: UNIX shell scripting (Basics)
Programming & Analytics: Data Integration & Transformation, Data Pipeline Automation, Machine Learning Fundamentals, Python, SQL
Industries: Insurance
Scheduling Tool: Autosys, Control M
Databases & Data Platforms: IBM DB2, Microsoft SQL Server 2017, Oracle, Snowflake