Sai Anuraag Gampa
Hyderabad
Summary
GenAI and Data Science professional with 3 years of experience designing and deploying intelligent AI systems across enterprise environments. Specialized in Retrieval-Augmented Generation (RAG), agentic workflows, vector search, and LLM-powered document intelligence using LangChain, FAISS, and modern LLM stacks. Proven track record of building scalable AI pipelines handling 600M+ records and delivering production-grade solutions in Agile environments.
Overview
3
3
years of professional experience
Work History
Data Science Analyst
Dun & Bradstreet
01.2023 - Current
- Designed and implemented an LLM-powered Super7 entity resolution system using RAG pipelines.
- Built document intelligence workflows to extract and categorize risk signals from annual reports.
- Contributed to internal MCP server architecture using FastAPI and JSON-RPC for agent orchestration.
- Developed LangChain-based multi-agent pipelines for resume intelligence and semantic matching.
- Engineered PySpark pipelines processing 600M+ records and optimized enterprise ETL workflows.
- Collaborated cross-functionally in Agile teams to deliver production AI and analytics solutions.
- Key Project Highlights
- Enterprise RAG pipelines and agent orchestration systems
- Vector similarity search implementation using FAISS
- MCP server (JSON-RPC + FastAPI) for internal AI tooling
- Large-scale PySpark data engineering pipelines
- LLM-based document intelligence and risk extraction
Education
B.Tech - Computer Science
CVR College of Engineering
Skills
- GenAI & LLMs
- RAG
- Agentic AI
- LangChain
- CrewAI
- Prompt Engineering
- LLM Integration
- FAISS
- Embeddings Pipelines
- Semantic Search
- Enterprise Document Intelligence
- Python
- PySpark
- SQL
- ETL Pipelines
- Large-scale Data Processing
- FastAPI
- REST APIs
- JSON-RPC
- Microservices
- Docker
- MCP Architecture
- AWS/GCP Exposure
- Git
- Agile/Scrum
Key Project Highlights
- Enterprise RAG pipelines and agent orchestration systems
- Vector similarity search implementation using FAISS
- MCP server (JSON-RPC + FastAPI) for internal AI tooling
- Large-scale PySpark data engineering pipelines
- LLM-based document intelligence and risk extraction
Timeline
Data Science Analyst
Dun & Bradstreet
01.2023 - Current
B.Tech - Computer Science
CVR College of Engineering