AI Engineer, Agentic Systems
Flybits · Full-time · Toronto
Agentic systems that plan, call tools across internal and partner APIs, and complete multi-step tasks with every decision logged for end-to-end auditability.
About
AI Research Engineer, working on the parts of an agent that fail.
I design the systems around LLMs — grounded tool use, retrieval, memory, failure recovery — and the evaluation that shows whether they hold. A Ph.D. in Computer Science sits behind that, but the work is engineering: research questions taken to running, measured software.
Biography
I am an AI Research Engineer based in Toronto, Ontario, Canada. My work sits where agent research meets production engineering: grounding an agent's outputs in real context, connecting models to tools, deciding what happens when a step fails, and building the evaluation loop that makes any of it checkable.
The through-line across my research is evidence. Project Ariadne asks whether an agent's stated reasoning actually caused its answer, and tests it by intervening on the reasoning and replaying the workflow. The planning work asks what a search should do when its heuristic stops informing it. The synthetic- data work asks whether generated examples improve a downstream classifier, not whether they look convincing. In each case the interesting part is the measurement.
I hold a Ph.D. in Computer Science from Toronto Metropolitan University, where my research focused on agentic AI workflows for reliable automated reasoning. I have published at AAAI, at Canadian AI, and in peer-reviewed journals, and I have worked across industry, government, and academia.
Open to research collaborations and selective advisory work in agent evaluation and reliability.
Current roles
One full-time engineering role and two research appointments.
AI Research Engineer, sAIpien
MIT Media Lab · Part-time research affiliation
Perspective-aware agents, privacy-preserving long-term memory, and benchmarks for transparency and human oversight.
Postdoctoral Fellow / AI Research Engineer
Toronto Metropolitan University · Part-time academic appointment · Toronto
Reproducible evaluation harnesses for LLM-agent reasoning, orchestration, context management, and reliability.
Previous experience
Machine Learning Engineer (Graduate Research)
Toronto Metropolitan University · Toronto
AI prototypes spanning multi-agent systems, heuristic search and planning, deep learning, reinforcement learning, and GAN-based synthetic-data generation.
ML Engineer / Research Scientist Intern
National Research Council Canada · Toronto
Knowledge-informed machine-learning models for anomaly detection over large-scale, severely imbalanced telemetry data.
Education
Ph.D. in Computer Science
Toronto Metropolitan University
Agentic AI workflows for reliable automated reasoning — LLM-agent orchestration, reasoning loops, tool use, and evaluation of agent faithfulness. GPA: A+. Coursework: Heuristic Search, Deep Learning, Directed Intelligent Robotic Systems.
Bachelor of Computer Science
Toronto Metropolitan University
A+ in every AI course: Machine Learning, Artificial Intelligence, Reinforcement Learning, and Computer Vision.
Research interests
- Agent faithfulness and causal evaluation
- Grounded tool use and orchestration
- Retrieval and long-term memory
- Failure recovery in multi-step workflows
- Heuristic search and planning
- Privacy-preserving and perspective-aware AI
Elsewhere
Other work
I'm also the founder of Ariadne Growth Systems, an independent growth-engineering company focused on measurement, automation, and customer-acquisition systems for service businesses. It is unrelated to Project Ariadne, the faithfulness-auditing research on this site — the name is shared, the work is not. Writing about growth engineering lives in its own archive.