ML Researcher & Engineer at the University of Waterloo.
Ethical AI · Reinforcement Learning · Multi-Agent Alignment
I'm a Master's student at the University of Waterloo researching ethical AI and reinforcement learning under the UWECEML Lab, with two papers (one accepted to AIES 2026). My work builds evaluation frameworks that surface misaligned agent behavior and training methods that respect human values — from single-agent ethical constraints to multi-agent enforcement.
Across 6 co-op work terms, I've applied ML and software engineering in industry — from building PyTorch computer vision models at Kindred AI to designing LLM-powered agentic systems at BrainRidge Consulting. I enjoy sitting at the intersection of research and engineering.
Outside of research, I'm drawn to the philosophical questions behind alignment: what does it mean for an AI to behave "ethically," and how do we measure that rigorously?
Building reinforcement learning agents that are both capable and aligned with human values — from single-agent ethical constraints to multi-agent enforcement. Graduate Research Assistant on the Moral AI Systems team at the UWECEML Lab, University of Waterloo.
Enforcing strict, non-linear ethical constraints in RL through a pipeline of Heuristic Oracles, Inverse Preference Learning (IPL), and Expected Scalarized Returns (ESR) over multi-objective rewards.
Studying when cooperation stays stable under self-interest. Dual-Enforcement RL pairs intrinsic constraints with social enforcement to close free-rider vulnerabilities in multi-agent systems.
Engineering JAX-native, Compute Canada-compatible training and evaluation pipelines on the high-dimensional Craftax environment — built for reproducible, large-scale agent-behavior benchmarking.
6 co-op terms and industry experience across ML, robotics, and software engineering.
Projects spanning ML systems, edge computing, human-robot interaction, and reinforcement learning.
Decentralized, edge-native predictive HVAC control with zero Age of Information — cut comfort violations by 76% and peak temperature overshoot by 90% versus centralized baselines.
Webots simulation investigating gender bias in human-robot interaction within educational environments using a humanoid NAO robot.
Self-adaptive urban traffic control system achieving a 45–49% reduction in average trip time across all traffic scenarios.
IoT personal air quality monitor — custom PCB, embedded BLE firmware, 3D-printed enclosure, and Android companion app. Built as a 4th year capstone.
University of Waterloo, one of Canada's top engineering programs.
I'm currently seeking ML research internships and full-time roles for 2026. If you're working on interesting problems in AI alignment, RL, or autonomous systems — I'd love to connect.