Hanan Ather

I am a Member of Technical Staff at the Centre for AI Research and Excellence (CAIRE) at Statistics Canada. I build full-stack AI systems and the evals that make them safe to deploy in confidential-data settings, with a focus on LLM evals, AI safety, and AI security. My research focus is on developing statistical methods for uncertainty quantification (conformal prediction, prediction-powered inference) and quality assurance of AI systems. Prior experience in SWE (full-stack), data engineering, and ML research (details in my CV). I am also a member of the Office of Responsible AI, where I lead technical reviews of AI systems across government and contribute to AI frameworks and governance guidance for UNECE, G7 GovAI, and the International Statistical Institute (ISI).

Projects

  • I built Probability Lab, an interactive probability and statistics platform currently in use at the University of Ottawa’s second-year engineering program.
  • I published a 6-part series of reinforcement learning labs (Jupyter notebooks): Reinforcement Learning Labs.

Graduate Course Notes

Papers & Publications