I'm Mohammad Abdullah, an AI engineer in Lahore. I build agentic systems, evaluation harnesses and the backend that runs them — for teams that need more than a demo.
From Python automation for freelance clients to production AI for Google and a full-stack AI platform.
Download résumé →Sole engineer on an AI lecture-generation platform, full stack.
Trained and fine-tuned LLMs for agentic task execution on first-party Android and iOS apps.
Built RAG pipelines with hybrid retrieval over Pinecone and FAISS.
Led backend for an Android TV app on AWS microservices; mentored a team of five.
Lahore, Pakistan.
The concrete systems behind each area of expertise — the things you can hire me to ship.
19 tools across 5 groups — sorted by where they sit in the stack.
Each one opens its own page: the problem, the system I built, and what changed.
Sole engineer on an AI lecture-generation platform — generation pipeline, background jobs, workspace and billing, end to end.
Training and evaluating agents that execute tasks on Android and iOS.
Read →INFOSTACKRetrieval on Pinecone and FAISS for fast, sourced answers.
Read →STAMPA SOLUTIONSLed a team of five building backend and automation systems.
Read →Pin down the real problem, the users and what success looks like.
Design the system — models, data, jobs and APIs — before writing code.
Prove the riskiest part first, so decisions rest on evidence.
Ship in small, working increments you can see and test.
Measure quality with real evals, then iterate on what the numbers say.
Monitor, harden and scale in production — and stay close for what comes next.
Hiring for an AI role, or need an agentic system built? Tell me what you're working on.