Principal OR/AI Scientist at Kinaxis · AI research and technical leadership
I build AI systems for reasoning, algorithm discovery, and optimization. At Kinaxis, I lead AI acceleration for a production solver and evaluation of coding agents. Previously, I led AI research for Huawei's OptVerse solver, shipped a routing engine used by 20+ enterprise customers, and developed OptvEvolve.
Our OptVerse-CityU team won first place in the 2026 CVRPLIB Best Known Solutions Challenge, with 51 new best-known solutions.
Research: agents and memory; algorithm discovery and learned search; language to formal models; optimization methods. Work includes MASPRM, SEDIMA, EvoCut, Latent Heuristic Search, COAgents, ORQA, NL4Opt, and AILS-Enhanced.
I connect AI proposals with reliable tests: feasibility, objectives, bounds, benchmarks, and held-out instances. My work has appeared at NeurIPS, AAAI, ACL, EJOR, and INFOR. I am lead inventor on multiple filed patents.
Ph.D. in operations research; postdoctoral fellow with Michel Gendreau at Polytechnique Montréal.