About
I'm a Machine Learning Engineer at Cresta AI, where I build and productionize LLM systems — fine-tuning and distillation, retrieval and reranking, and agentic Q&A — for quality-critical applications in call-center AI.
Before Cresta, I was an AI Research Scientist at LG Toronto AI Lab, and I completed my Ph.D. in Electrical and Computer Engineering at Queen's University, where my research focused on natural language reasoning with diverse knowledge sources.
My current focus is on post-training methods, agentic retrieval, and rigorous evaluation of LLM-based systems.
Experience
-
Machine Learning Engineer
Jul 2023 — PresentCresta AI · Toronto, CanadaBuilding RAG, agentic retrieval, and in-house LLMs for call-center knowledge assistance.
- Productionized an in-house query rewriter via LoRA fine-tuning and teacher-model distillation, matching frontier-LLM quality at a fraction of the serving latency and cost.
- Fine-tuned a lightweight gating classifier that decides when to trigger retrieval, reducing unnecessary LLM calls without hurting answer quality.
- Improved retrieval relevance through hybrid search, LLM-based document expansion, and in-house reranker fine-tuning.
- Shipped an agentic retrieval system as the default retrieval layer for production Q&A agents, and built LLM-as-a-Judge evaluators for systematic offline evaluation.
-
AI Research Scientist
Oct 2022 — Jun 2023LG Toronto AI Lab · Toronto, CanadaBuilt an in-house retrieval-augmented language model (Fusion-in-Decoder + distillation) for open-domain QA, with scalable distributed training and sub-500ms retrieval via FAISS + product quantization.
-
Machine Learning Research Intern
Jun — Aug 2022Microsoft Research · Montréal, CanadaResearched compositional generalization in semantic parsing, exploring attention regularization and syntax-semantics disentanglement.
-
Machine Learning Research Intern
Jun — Aug 2021Samsung Research America · Mountain View, USAImproved neuro-symbolic visual concept learning with knowledge-aware supervision, increasing model accuracy and training efficiency on visual question answering.
-
Machine Learning Engineer Intern
Jun — Aug 2018Alibaba DAMO Academy · Hangzhou, ChinaDeveloped a neural information extraction model for insurance policy documents, improving extraction accuracy through attention mechanisms.
Publications
More on Google Scholar →
Education
-
Ph.D., Electrical and Computer Engineering2018 — 2022Queen's University · Ingenuity Labs
-
M.S., Information Engineering2016 — 2018University of Chinese Academy of Sciences
-
B.E., Computer and Control Engineering2012 — 2016Nankai University