I am an Part-Time Lecturer at Murang'a University of Technology in the Department of Computer Science. I am a postgraduate researcher at MUT working with Federated Learning.
My research focuses on principled approaches to privacy-preserving AI, combining insights from optimization, statistics, and economics to design trustworthy AI systems.
What does it mean for complex AI systems to be safe or private? How can we audit, measure, and improve it? How can we measure and improve LLM behavior?
What makes training data "good" and how do we define "good"? What makes for good benchmarks given we are far from the simple i.i.d. splits ML used to assume?
How can we understand and shape the complex "machine behavior" arising from interacting humans and AI agents? How can we ensure the health of such ecosystems?
Can we translate these solutions to address bottlenecks for deploying AI in high-stakes healthcare settings?
Submitted my Systematic Literature review at IJESE for review and further publication.
Successfully presented my Thesis Seminar 1 (Objective 1) at MUT postgraduate presentation..
Successfully presented my Thesis Proposal at MUT postgraduate presentation.
Successfully presented my Thesis Concept at MUT postgraduate presentation..
Started Part-Time work teaching at MUT Computer Science.
Started my Master's program at MUT in Computer Science.