AI Engineer · Full-Stack Developer
RAG platforms, tool-calling agents, multi-agent workflows, AI automation, and the full-stack products around them. Grounded outputs, real evals, production architecture. Five years of shipping for clients, startups, and now enterprise-grade AI.
Muhammad Afzaal Afzal
AI Engineer & Full-Stack Developer
Selected work
Not demos: systems with retrieval quality reports, traces, guardrails, and human approval flows.
Teams ask questions; their answers are buried in hundreds of PDFs.
Contextual RAG pipeline with PDF ingestion, chunking, Chroma vector search, and hybrid retrieval. Answers ship with citations, and Ragas evals feed a quality dashboard so retrieval regressions are caught, not guessed.
One agent can answer a question. Real workflows need several that cooperate.
Supervisor and specialist agents collaborating through shared state, checkpoints, and human-in-the-loop approval. Every run produces a full multi-agent trace, so behavior is debuggable instead of magical.
Support teams drown in repetitive tickets that follow known playbooks.
Tool-calling agent that searches docs, summarizes issues, and creates tickets, all behind guardrails, tracing, and a human approval step for anything irreversible.
Answers live half in documents, half in database rows. Most copilots pick one.
Hybrid answers across documents and SQL with record-level citations, row-level access control, and governance reports. Data-agent workflows that respect who is asking.
Try it
A scaled-down version of the retrieval systems I build, running entirely in your browser: keyword scoring over this site's content, a citation on every answer, and a grounded refusal when it does not know.
How I work
It needs structure, safety, evaluation, and a clear user workflow. Five rules I build by:
Define the user, the business goal, and the expected outcome before writing a line of code.
Separate UI, API, AI provider logic, tools, storage, evals, and observability, so each can change without breaking the rest.
Citations, retrieval checks, refusals, validation, and structured responses. An answer you cannot trace is a liability.
Track latency, cost, retrieval quality, eval scores, and regressions. If it is not measured, it is broken and nobody knows.
Logging, retries, timeouts, security checks, deployment docs, and clean READMEs. Shipping is part of the system.
Writing
Contact
Full-time, freelance, or a startup MVP that needs to exist. If it involves LLMs, retrieval, agents, or a product around them, I am interested.