I build production AI systems and the full-stack products around them. Over seven years I've shipped RAG pipelines, multi-agent workflows, voice agents, OCR and computer vision systems, along with the React, Next.js, Angular, Node.js, Django, and FastAPI applications that put them in front of real users.
Most recently at Turing, I worked as a Senior LLM Engineer on Terminal-Bench and trained computer-use agents for Meta. That meant writing the tasks, evaluations, and validation pipelines that frontier models are tested against. Before that I was a Tech Lead at Devsinc running a team of seven engineers, and an ML Engineer at PackageX building OCR and document processing for logistics.
My work spans logistics, fintech, healthcare, HR, education, e-commerce, and construction estimation. Recent products include an AI grading platform, a compliance automation tool, and a contractor estimation system, each built from architecture through deployment.
I care about software that holds up in production: clear architecture, tested code, structured LLM outputs, and automation that saves people real time. I hold an MS in AI from NUST and a BS in Computer Science from FAST-NUCES.