I'm a Computer Engineering student (UAlberta, Software Option Co-op, graduating June 2028) who
builds end-to-end systems: the machine learning that makes decisions, and the full-stack platforms
that put those decisions in front of the humans who act on them.
At BossPac Engineering & Technology, I owned the MLOps layer of a production broken-rail anomaly detection system — broken rail being a leading cause of mainline freight derailments. The model's predictions, coupled with dispatch policy, cut false-positive alerts by ~52% in live operation across Class 1 freight subdivisions in North America. My work is the applied-ML workflow around them: data cleaning and normalization, feature engineering, retraining experiments, rebaselining, per-subdivision scaler and drift management, and precision/recall evaluation against confirmed field outcomes.
I also built the full-stack platform that operationalizes it. BRIM runs on the PERN stack (PostgreSQL, Express, React, Node.js) deployed on AWS with Redis session management, AWS Cloudscape components, and Cypress and Jest test suites — delivering real-time geospatial alerts, configurable condition-based dashboards, and field-deployment tooling to 10–50 rail operators monitoring 7,000+ sensors across ~2,000 instrumented mileposts of Class 1 freight railway. I worked across the stack: REST APIs on Node/Express, PostgreSQL schema and query tuning, role-based access tiers, AWS and Apache administration, production validation testing, the deployment runbook the team ships from, and the operator user guide. The ML is only useful because the platform makes it legible to the humans making safety calls.
I also built a site-wide PLC diagnostic web app covering 50+ process units, adopted daily by ~10 engineers and technicians — replacing a diagnosis path that required a trip to the control room, area authorization from the site manager, and layered system logins. On the side, I work as an AI Evaluation & Post-Training Contractor at Outlier AI, authoring evaluation rubrics and adversarial prompts for frontier multimodal models across 310 technical tasks in math, science, software engineering, data science and ML.
I'm looking for teams where both sides of the stack matter — where the model has to work in
the field and the interface has to work for the user. Industrial AI, autonomous systems,
robotics, safety-critical infrastructure, and applied AI at companies that care about the gap
between a model in a notebook and a model in production. I'm equally happy owning general
full-stack or backend work at companies building things that matter; the common thread is
real-world systems where correctness, reliability, and human trust are non-negotiable.