AI systems engineering, end to end.
I'm a Senior Full Stack Developer and AI Engineer with 5+ years building web platforms and AI systems for startups and enterprises, having led 10+ products from conception to deployment. Most recently, I've been building LLM evaluation pipelines that route across multiple providers and content modalities in production.
I care about shipping systems that hold up in production: clean APIs, sane data models, and infrastructure that scales without drama. Based in Lahore, Pakistan, working remote with teams worldwide.
Operating Profile — one engineer across model, API, and interface
AI Systems & Evaluation
Architected an internal LLM evaluation platform running high-volume async evaluations, with a 2-stage pipeline pairing parallel primary evaluators against meta-evaluator aggregation. Built multi-modal RAG pipelines (text, documents, images, audio, video) with LangChain and LangGraph, routing and failing over across 4 LLM providers — OpenAI, Anthropic, Google, and Fireworks.
Full-Stack Engineering
10+ products shipped end to end: React/TypeScript front ends backed by Python and Node.js services — FastAPI, Express, Nest.js — on PostgreSQL, MongoDB, and Redis. Comfortable owning a feature from data model to deployed UI.
Infrastructure & Reliability
Real-time streaming over WebRTC/WebSockets with GCP Pub/Sub, containerized with Docker and Kubernetes, deployed via Helm and CI/CD. Consolidated region-by-region API scans into a single aggregated call to cut operational overhead.
Core Stack