About

I build software and study how agents use it

I study AI agents where software systems, security boundaries, and operational evidence matter. The aim is to make agent behavior inspectable before it is trusted.

Research

Inspectable agents in real systems

I study how AI agents behave in real software systems—and how to make their decisions inspectable, reliable, and trustworthy.

Current work combines reliability-agent evaluation, security audits for agent choices, and developer tools that make context and software evolution easier to examine.

Research dossierPublications

Engineering

About three years building production systems

About three years of professional software-engineering experience, formerly at IQVIA. Selected engineering records emphasize owned systems, measurable outcomes, and direct proof rather than a full technology inventory.

Experience recordEngineering projectsOpen-source contributions

Background

From BUET systems work to Alberta research

I completed a B.Sc. in Computer Science and Engineering at BUET CSE and have built backend systems, data workflows, and developer tools alongside research collaborations. The thread across that work is practical: make complex systems easier to understand, test, and improve.

M.Sc. in Computing Science at the University of Alberta, beginning September 1, 2026.

EducationCV

Conversation

Research and engineering conversations

If you are studying dependable AI agents or building reliable software systems, I would be glad to compare research questions, evaluation evidence, or engineering tradeoffs.

Email TanzimResearch dossierCV