Engineer · Researcher · ex. US Faculty Member
Rust · Python · Java · SPEC-driven development · vibe coding

Haoyi "Bertrand" Xiong熊昊一

I design and ship Agentic AI systems at web-scale...

Ph.D. in Computer Science from Télécom SudParis / Université Pierre et Marie Curie, France (2015). Postdoc at University of Virginia, then tenure-track Assistant Professor at Missouri S&T. Since 2018, held technical staff roles at Baidu and Microsoft. This is a personal site — opinions are my own.

// What I build

Agentic AI Systems

Autonomous AI agents with LLM-powered function calling, tool use orchestration, and multi-step reasoning.

LLM Agents Function Calling Tool Orchestration
🔍

Data Science, ML & Search

Next-gen search fusing LLMs with learning-to-rank, multi-objective optimization, and KV cache pruning at web-scale.

Learning to Rank Web Search LLM + Search
🧪

ML Systems & Infra

Production ML platforms serving billions of requests — model-as-a-service, distributed GNN training, multi-GPU graph learning.

Distributed ML MLOps GNNs
🧬

AI for Science

Deep learning for scientific problems — RNA language models, molecular pre-training, protein-ligand binding, PDE surrogates.

Molecular LMs Drug Discovery XAI

Awards & Honors

2025
Fellow of the Institution of Engineering and Technology (FIET)
IET, United Kingdom
2025
Best Paper Award
Knowledge and Information Systems (KAIS)
2023
Best Student Paper Award
IEEE ICDM
2023
Best Paper Award — Journal Track
IEEE DSAA
2020
Excellence in Scalable Computing (Early Career)
IEEE Computer Society TCSC
2019
First Prize, Science & Technology Advancements Award
Chinese Institute of Electronics (for PaddlePaddle)

Community

Get in Touch

Always interested in hard problems — agentic AI, search, and systems that scale.

GitHub Google Scholar LinkedIn X Blog