About
I am curious about language, data, and how models behave in the real world. My work sits at the intersection of natural language processing, information extraction, terminology, and large language models—often in multilingual and specialized domains (science, institutions, low-resource settings).
I care about open research, teaching, and building things that other people can reuse—whether that is a paper, a course, or a product demo shipped with a team.
Experience
Founder — Tihado
Jan 2025 - Present · Paris, France
Co-building Tihado and its product bets with the team—including recognition such as 1st place (Creativity) at the Agents & MCP Hackathon 2025 for Vidzly, and 3rd place at the AMD Open Robotics Hackathon 2025 for EatAble.
NLP Engineer — ARKHN
Sep 2024 - Present · Paris, France
Applied NLP for health-data and research contexts: pipelines, evaluation, and models in production-oriented research environments.
Lecturer — VietAI
Jan 2022 - Present · Vietnam (remote / hybrid)
Teaching and curriculum around generative AI and practical ML—courses such as Generative AI for Everyone, Build Applications with the OpenAI API, and ChatGPT / Bard for Everyone.
Doctoral researcher — Jožef Stefan Institute & La Rochelle Université
Oct 2021 - Sep 2024 · Ljubljana, Slovenia & La Rochelle, France
PhD in a cotutelle program between La Rochelle University, France and Jožef Stefan Institute, Slovenia, supervised by Prof. Antoine Doucet and Assist. Prof. Senja Pollak. Focus: NLP, terminology extraction, cross-lingual transfer, and related machine learning.
Invited researcher — Jožef Stefan Institute
Feb 2021 - Sep 2021 · Slovenia
Short research stay preceding the doctoral program.
Data Scientist — Samsung SDS Vietnam
Earlier career stage in applied data science and engineering (prior to the doctoral program).
Education
PhD — Computer Science / NLP (cotutelle)
La Rochelle Université & Jožef Stefan Institute · 2021 - 2024
Thesis work on terminology and NLP in specialized and multilingual settings.
MSc
University of Montpellier, France · 2019 - 2020
BSc
University of Science and Technology of Hanoi (USTH), Vietnam · 2014 - 2017
Licenses & certifications
- Google Associate Cloud Engineer — Jun 2025
- Advanced Data Science with IBM Specialization — Coursera · Nov 2020
Honors & awards
- 1st place — Creativity Award, MCP 1st Birthday Hackathon (Anthropic, Hugging Face, Gradio) — Dec 2025
- 3rd place, AMD Open Robotics Hackathon (AMD, Hugging Face, WowRobo, Data Monsters) — Dec 2025
- Best Paper Award, TPDL 2024 (28th International Conference on Theory and Practice of Digital Libraries)
Selected publications & outputs
Representative topics: keyword extraction with mixture-of-experts, LLM-assisted terminology extraction, digital libraries, and historical / multilingual NLP. A full list lives on Google Scholar and hanh.zootopi.dev.
Examples (titles shortened for readability):
- SEKE: Specialised Experts for Keyword Extraction — Findings of EMNLP, 2025.
- LlamATE: Automated terminology extraction using large-scale generative language models — Terminology, 2025.
- Cross-domain / cross-lingual term extraction — Machine Learning, 2024.
- Historical newspaper layout / multimodal structure — TPDL proceedings, 2024.
Languages
- Vietnamese — Native
- English — Professional working proficiency
- French — Working proficiency
- Spanish — Basic
Profile details on this page are maintained from public professional sources and may be summarized. For the full timeline, see LinkedIn and hanh.tihado.com.