I build AI agents and the LLM backends behind them: RAG search, tool use and production APIs. 8+ years of production Python, now working toward Forward Deployed Engineer roles and studying for CCAR-F in public.
Ask about my work and get an answer with its source. The agent reads only a profile I wrote and approved, and says so when the profile does not cover a question.
Answers come only from a profile Zeeshan wrote and approved. Your question is sent to Anthropic's Claude to write the answer. Don't include anything private.
Built
A platform that crawls any public website, converts its content into structured data, audits it for AI search visibility, and recommends fixes. I built the universal scraping layer, the core AI modules and the backend that scores and tracks content in real time.
Built
A centralized AI search engine using Retrieval-Augmented Generation, shipped in 2024. It keeps products in sync from four backend systems, serves three frontends through one search API, handles complex product catalogs with many variations in size, model, memory and storage, and solved the client's main search problem.
Built
I led the development of a distributed scraping system that cut end-to-end processing time from 4.5 hours to under an hour, about 75%, and lowered infrastructure cost by about 40%.
Built
A search workflow you can talk to. I integrated a voice API, converted speech to text, and passed the transcribed query into a retrieval-augmented pipeline that returns relevant results from indexed knowledge sources.
My map of Anthropic's four Claude exams. I am studying for the first one and hold none of them yet.
Forward Deployed Engineer and AI agent engineering roles. That means work where an ambiguous requirement becomes a working prototype, and then a reliable production service.
I am based in Lahore, Pakistan. I am open to relocation and travel: Riyadh or Dubai.
Yes. My current role at Diametos GmbH, a German medical-technology company, is remote. I work daily with a Germany-based engineering team and keep EU-hours overlap.
Python, Django, FastAPI and Go on the backend, on AWS (Lambda, API Gateway, Cognito). PostgreSQL, MongoDB, Redis and DynamoDB for data. On the AI side: Claude, OpenAI, LangChain, RAG, vector search, structured outputs, and tool and API integration.
DeepSerp, an AI SEO/GEO optimization platform. A hybrid search engine (vector plus text) for product catalogs, built with RAG. And a voice-enabled RAG search that answers a spoken question from indexed knowledge sources. Each one has its own page under Projects.
CCAR-F is Claude Certified Architect: Foundations, a certification exam from Anthropic. I have not earned it yet. I am studying for it and publishing my session notes on this site.
No. A badge is not a certification, so each item is labeled as what it is: completion badge, skill badge, course certificate or certification. The Credentials page shows which is which.
Use the Contact page on this site to hire me, ask for a consultation call, or send a message. You can also message me on LinkedIn. My resume is on this site as a PDF, with the same experience as the About page.