AI professional with 2 years of experience in developing Generative AI, LLM, RAG, and Agentic AI solutions for enterprise use cases. Hands-on experience with Python, LangChain, LangGraph, GPT, Claude, Gemini, vector data…
AI professional with 2 years of experience in developing Generative AI, LLM, RAG, and Agentic AI solutions for enterprise use cases. Hands-on experience with Python, LangChain, LangGraph, GPT, Claude, Gemini, vector databases, APIs, AWS, and Azure. Experienced in building AI-driven document automation, knowledge management, contract analysis, and intelligent workflow solutions to solve real-world business problems.
الخبرة
Z
AI Analyst
ZEB / AVASOFT·Chennai, India
Oct 2024 - Aug 2026 · 1 سنة 10 أشهر
<p>Designed and built a self-service, searchable wiki to replace a manual, scattered document-review process, using an agentic pipeline with entity extraction and schema management — reduced time spent locating past project documentation by 90%.</p><p> Developed and deployed the RAG retrieval and schema layer that indexes knowledge across 500+ past projects into a single searchable source.</p><p> Built a RAG-based system that reviews vendor and customer contracts for a logistics client, retrieving relevant company policy sections from PostgreSQL and using GPT to flag discrepancies between contract clauses and policy.</p><p> Automated Microsoft Word Track Changes and comments to strike out non-compliant clauses and add suggested corrections, so legal teams can review the output directly in the document and spend less manual effort on it.</p><p> Developed the end-to-end pipeline (API-based document submission, chunking, similarity search, LLM analysis) and exposed it through a chatbot/API interface.</p><p> Developed and deployed API-based AI tools that retrieve organizational context through RAG, generate SOW/LOE content with GPT, and auto-populate Word templates — reduced drafting and formatting time from 1-2 days to approximately one hour, an 85% reduction in manual effort for sales and technical teams.</p>
المشاريع
N
NFI Redlining
Zeb
المدة : 10-Mar-2026 - 10-Aug-2026
01 · Problem<p>Legal teams needed a more efficient way to identify discrepancies between vendor/customer contracts and internal company policies.</p>02 · Solution & architecture<p>Processed documents submitted through a chatbot/API, chunked the contract text, retrieved relevant policy passages from PostgreSQL using semantic similarity, and sent the contract chunks plus retrieved context to GPT for analysis.</p><p>Document via chatbot / API→Ingestion & chunking→PostgreSQL policy search→RAG context + GPT→Word Track Changes & comments</p><p>Potential discrepancies were shown directly in the Word document by striking through flagged text and adding suggested corrections as comments for legal review.</p>03 · My role<ul><li>Developed the document-processing workflow, chunking, similarity search, and LLM analysis.</li><li>Implemented the RAG pipeline over company policy content stored in PostgreSQL.</li><li>Integrated GPT-based clause comparison and Microsoft Word Track Changes/comment automation.</li><li>Helped connect the workflow to chatbot/API-based document submission.</li></ul>04 · Results<p>Delivered a working POC that helped surface policy deviations faster and placed proposed corrections in the document for legal teams to review, reducing manual review effort.</p>05 · Tech stack<p>Python · GPT · RAG · LangChain · PostgreSQL / vector search · FastAPI / REST API · NLP · Microsoft Word automation</p><p></p>
الشهادات
Databricks Certified Machine Learning Professional
