AI/ML Engineer & Data Scientist in Islamabad, finishing an MS in Data Science at Quaid-e-Azam University. I build LLM agents, retrieval systems and data products, and I measure whether they work: held-out test splits, ablations, confidence intervals, and honest write-ups of what did not.
🟢 Open to AI/ML engineering, data science and ML research roles: onsite or hybrid in Islamabad/Rawalpindi, or remote.
| Project | What it is | Result |
|---|---|---|
| Data Analyst Agent | Self-correcting text-to-SQL agent (LangGraph): schema linking, read-only SQL guard, literal-value check, fix loop | 60.7% → 66.7% execution accuracy on held-out BIRD questions (+6.0 pts, 95% CI [+1.3, +11.3]) |
| E-mail Experiment & Uplift | Full readout of a 64,000-customer randomized experiment: SRM, Holm-corrected effects, CUPED, peeking, uplift models, IPW policy value | Men's e-mail +$0.77 spend per customer; blanket sending beats model targeting below ~$0.23/e-mail |
| Customer-Ops Agent | Support agent that takes real actions behind a gateway: policy in code, confirmation codes, human approval via interrupts, idempotent refunds | 45 tau-bench-style scenarios incl. prompt injection and tool failures (evaluation running) |
| Financial RAG Lab | Which RAG choices matter? Chunking, metadata scope, BM25/dense/hybrid, rerankers, HyDE on FinanceBench | 45 retrieval configs on 84 filings, scored on evidence pages (experiments running) |
| Literature Review Agents | Multi-agent reviewer (arXiv + OpenAlex) where every finding quotes its source verbatim and a critic checks citations | Independent, validated LLM judge vs a single-agent baseline (evaluation running) |
Also: Qanoon Assist (private), a legal-information RAG over 117,365 sections of Pakistani law in English, Urdu and Roman Urdu (hit@5 1.00, faithfulness 0.944); and my MS thesis UrduComicLab, complete Urdu stories → right-to-left comics with open-weight models (spoken lines printed 0.49 → 1.00 vs baseline).
LLM agents & RAG: LangGraph, function calling, multi-agent pipelines, hybrid retrieval, cross-encoder reranking, evaluation & guardrails ML & stats: PyTorch, LightGBM/XGBoost, Vision Transformers, A/B testing, causal inference, uplift modeling Engineering: Python, SQL, FastAPI, Docker, React, pytest
The quickest way is e-mail or LinkedIn. CVs are on my portfolio.