Hi there, I'm Abdulmalik
AI Engineer and Researcher building and evaluating production multi-agent systems.
About Me
I'm an AI Engineer and researcher currently pursuing an M.Eng in Computer Science at Nagoya Institute of Technology. My work sits at the intersection of building and evaluating multi-agent LLM systems: I design and deploy them for real users, and I research the architectures and evaluation methods that make them reliable.
On the engineering side, I've built production AI systems across healthcare, education, and decentralized finance, including a multi-agent mentoring platform currently in active use by research students at Ozlab (NITECH), a voice-AI student risk management system, and a natural-language analytics platform for Solana DeFi data.
Skills & Technologies
AI and LLM Engineering
Web and Application Development
ML and Deep Learning
Data Engineering
Infrastructure and MLOps
What I Do
From research questions to production deployments, I work across the full lifecycle of multi-agent AI systems.
Building Production AI Systems
I design, build, and deploy multi-agent LLM systems for real users, owning the full stack from agent architecture and prompt engineering to web interfaces and live deployment.
Researching How to Make Them Reliable
I study evaluation methods, human-in-the-loop architectures, and governance mechanisms for multi-agent AI, with peer-reviewed work on contestable AI and supervisor-in-the-loop adaptive memory.
Bridging Both
My research projects deploy with real users, and my engineering work feeds back into research questions about evaluation, reliability, and human oversight.
Let's explore how I can contribute to your team
Get in touch 👋
