Builder. Researcher. Explorer
How can autonomous systems reason and act reliably under uncertainty?
Machine Learning Engineer @Huawei R&D. MSc Intelligent Systems (CV & Robotics) at @EDISS (Erasmus Mundus Scholar). Previously, built Adpay at @Mercurie NG.
Check out my writings here, or on Substack for more spiritual and theological topics. Feel free to reach out for anything!
Our paper "Beyond Suffixes: Token Position in GCG Adversarial Attacks on Large Language Models" was accepted at the ICLR ICBINB 2026 Workshop.
Graduated from the EDISS master's program. My thesis on Adaptive Bathymetric Planning can be found here.
Presented ongoing work on Parkinson's detection & biomarker discovery at the EDISS Winter School in Västerås.
Won the Nokia Challenge Hackathon for network bandwidth optimization with NetworkAsCode.
Began the EDISS joint master's (Finland & Spain) on an Erasmus Mundus scholarship.
Ran a workshop on digital skills for recent university graduates in Abuja.
Beyond Suffixes: Token Position in GCG Adversarial Attacks on Large Language Models
Hybrid MCTS–CEM for Adaptive Bathymetric Planning
Multi-agent web text collector with planner, explorer, harvester, and auditor agents plus LLM-as-a-Judge quality control.
Hybrid MCTS and Cross-Entropy planning framework for adaptive bathymetric mapping with autonomous underwater vehicles.
LLM agents from zero to hero — design patterns for tool use, planning, and memory.