Software engineer working on mobile apps, LLM systems, and applied ML research. Final-year Software Engineering student, based in Pakistan, open to remote work.
I build AI systems and then try to measure whether they actually work. My focus is on retrieval, agents, and evaluation, and I work in Flutter and Python.
Reliable LLM systems: retrieval, chunking, hybrid search, knowledge graphs, and multi-agent workflows, with evaluation built in from the start rather than added at the end.
Scientific and applied ML: I'm interested in using ML and LLM agents on scientific problems, and I'm working toward contributing to open-source research projects in this area.
Mobile engineering: production-minded Flutter apps with clean architecture, state management, and Firebase or Supabase backends.
- Measure before claiming. I compare designs with benchmarks and LLM-as-judge or RAGAS evaluations instead of relying on intuition.
- Build in the open. Experiments, failures, and write-ups go in public repos and on Medium.
- Reproducible by default. Clear READMEs, pinned dependencies, and tests wherever the result matters.
- Learn by building. I understand things properly once I've implemented them.
I'm looking to contribute to open-source projects in LLM tooling, agentic systems, and scientific ML, and to take on research-style work where the question matters more than the demo.
If you maintain something in this space and have a good-first-issue or a research question that needs another pair of hands, I'd like to hear from you.
LangChain · LangGraph · ChromaDB · RAGAS · Groq · scikit-learn · Pandas · NumPy
Outside work: history, geography, and writing about the threads connecting places and cultures.