Professional Summary
GenAI Engineer with 3+ years of experience building and deploying production-grade LLM systems. Expertise in Retrieval-Augmented Generation (RAG), multi-agent workflows, and end-to-end AI application development. Proficient in Python, SQL, LangChain, LangGraph, OpenAI API, Groq, and vector databases (FAISS/ChromaDB/pgvector). Strong experience in prompt engineering, embedding pipelines, RAG evaluation (RAGAS), and hallucination control. Skilled in developing scalable APIs (FastAPI/Flask), data pipelines, and deploying AI solutions on cloud platforms. Proven ability to design intelligent agentic systems and convert business requirements into production AI products. Seeking GenAI Engineer roles (Remote/Hybrid) to build scalable, high-impact LLM-powered systems.
Professional Experience
Senior Software Engineer – GenAI & AI Systems
Architected and deployed production-grade GenAI systems using RAG, multi-agent workflows, and tool-calling LLM pipelines for airline revenue intelligence.
Designed scalable LangChain/LangGraph-based agentic architectures integrating SQL engines, vector databases (FAISS/ChromaDB), and memory modules.
Built secure Text-to-SQL pipelines with validation layers ensuring safe query execution over large airline datasets (millions of records).
Implemented end-to-end LLM deployment using Azure OpenAI and Groq APIs with prompt engineering and response optimization.
Created high-performance backend services using FastAPI and Flask for seamless AI-driven API integration.
Optimized retrieval latency and response quality through embedding tuning, chunking strategies, and caching mechanisms.
Delivered AI analytics assistants improving decision-making across route performance, POS analysis, and revenue optimization.
PythonLLMs (GPT / Azure OpenAI / Groq)RAG
LangChainLangGraphFAISS
ChromaDBSQLDuckDB
FastAPIFlaskDocker
Software Engineer – Airline Forecasting & Revenue Systems
Developed airline demand and revenue forecasting pipelines supporting commercial strategy and pricing decisions.
Engineered KPI pipelines for Revenue, Passengers, Load Factor, and Yield with standardized metric computation.
Built route/POS-level performance analytics comparing Current vs Last Year vs Target trends.
Improved forecasting data reliability through data cleansing, feature engineering, and pipeline automation.
PythonSQLPandas
SQL ServerScikit-learnForecasting Models
Data Pipelines
Key Projects
01
Advanced RAG Chatbot
LangChain · ChromaDB · Cross-Encoder · Groq · Flask
Production RAG system with bi-encoder retrieval, cross-encoder re-ranking, sliding-window memory, and RAGAS evaluation.
02
Finance AI Agent (Multi-Agent LLM System)
LangGraph · Groq Llama 3.3 · GPT-4o · yfinance · Streamlit
Adversarial multi-agent investment committee — Bull/Bear debate, Risk Auditor, CIO Judge, human-in-the-loop PDF report.
03
SalesQuery AI (NL2SQL)
Llama 3.2 · HuggingFace Hub · Gradio · SQLite
Fine-tuned Llama 3.2 1B on 1000+ custom NL-SQL pairs; deployed live demo to HuggingFace Spaces.
04
Text2Insight
FastAPI · DuckDB · SSE Streaming · Vanilla JS
Full-stack NL-to-SQL analytics platform with JWT auth, multi-turn memory, confidence scoring, and PDF/PPT export.
05
DataPilot-MCP
MCP · DuckDB · Python
Conversational data analytics agent on Model Context Protocol — plain-English SQL queries, auto-charts, narrative summaries.
06
VisionRAG
GPT-4o Vision · pgvector · PostgreSQL · FastAPI · Docker
Multimodal RAG for scanned PDFs and invoices — visual layout understanding, page-level citations, Docker Compose deployment.
07
LLMWatch
LangChain · LangGraph · RAGAS · LangSmith · SQLite · Streamlit · GitHub Actions
Plug-and-play LLM observability platform — tracks cost/query, P50/P95/P99 latency, token usage, RAGAS hallucination rate. CI eval gate auto-fails PR if quality drops below threshold.
Technical Skills
| LLM / Agents | LangChain, LangGraph, CrewAI, LlamaIndex, AutoGen |
| AI APIs | Groq, OpenAI, Azure OpenAI, Ollama |
| RAG / Vector | ChromaDB, FAISS, Pinecone, BM25, pgvector |
| Evaluation | RAGAS, LLM-as-Judge, Hallucination Control |
| Backend | Python, Flask, FastAPI, DuckDB, SQL, Docker, Git |