Skip to content

Latest commit

 

History

History
107 lines (67 loc) · 5.24 KB

README.md

File metadata and controls

107 lines (67 loc) · 5.24 KB

My Tech Stack

Hey, I'm Shaad Ahmad

GenAI & Agentic AI Consultant · Full-Stack Builder

Agentic RAG, multi-agent orchestration and full-stack AI. Designed, built and shipped end to end.

I take GenAI engagements on my own, from scoping through build, deployment and handover. Currently also building Cardoo, a digital identity app for India 🇮🇳

Website Book a call LinkedIn

GitHub followers Profile Views


What I Build

Capability What it means
Agentic RAG Hybrid retrieval, cross-encoder reranking and metadata filtering over your own knowledge base
Multi-Agent Orchestration Stateful, tool-calling agents that plan, act and hold context across long-running workflows
LLM Application Backends Typed APIs, structured outputs, streaming and schema validation wrapped around the model layer
Document Intelligence OCR and layout-aware parsing that turns unstructured documents into clean, queryable data

Every system ships with cost controls, schema validation and a human in the loop, because a demo that impresses is not the same as one you can run on Monday.


Shipped to Production

Engagement What it does
Legal Agentic RAG
Production RAG over 50,000+ contract and legal PDFs. Hybrid BM25 plus dense retrieval with cross-encoder reranking, which cut the hallucination rate measurably.
AI Hiring Automation
A 7-stage pipeline from job post to onboarding that removed roughly 95% of the HR workload per hire, leaving just 3 human decision points.
RFQ to Quotation
Email in, techno-commercial offer out. Nothing reaches a customer without human approval.

Tech Stack

Python AWS Docker CI/CD GitHub Actions Git GitHub

GenAI Engineering

LangChain LangGraph LangSmith Hugging Face Vector DB promptfoo

Techniques: hybrid BM25 and dense retrieval · cross-encoder reranking · metadata filtering · tool-calling agents · structured outputs · schema validation · OCR and layout-aware parsing · tracing, evaluation and token budgets

Techniques: hybrid BM25 and dense retrieval · cross-encoder reranking · metadata filtering · tool-calling agents · structured outputs · schema validation · OCR and layout-aware parsing · tracing, evaluation and token budgets

Get in Touch

Book a call Email LinkedIn GitHub

"AI isn't about generating text. It's about systems that reason, act, and hold up in production."