Khang Tran

Minh Khang Tran

Machine Learning Engineer  ·  Computer Vision & LLM Systems

Paris, France  ·  Open to Machine Learning and Research Engineer roles

I build computer-vision and LLM systems and take them to production. In two years of industry work I built a multi-agent assistant serving hundreds of requests a day, an OCR pipeline that reads handwritten medical forms at 2,000 images an hour, and face-recognition serving on Kubernetes. I recently completed an Erasmus Mundus MSc in Computational Colour and Spectral Imaging (admitted 1st of 198) and co-authored a paper that won the Best Student Paper Award at IS&T Electronic Imaging 2026.

Research Interests

  • Vision-language and multimodal models
  • Colour, illumination, and physically grounded training signals
  • Data-efficient and self-supervised learning
  • ML systems in production: serving, evaluation, reliability

Education

  • MSc Computational Colour and Spectral Imaging (Erasmus Mundus) NTNU · Université Jean Monnet · University of Eastern Finland 2024–2026  ·  Grade: Very Good
  • BSc Computer Science SUNY Oswego 2019–2022  ·  Summa Cum Laude, GPA 3.81 / 4.0
2026.09 Defended my Master's thesis on Cross-Illumination Albedo Invariance, at NTNU, completing the Erasmus Mundus COSI programme.
2026.03 Received the Best Student Paper Award for Adapting DeQA-Score for Attribute-Specific Portrait Quality Assessment at IS&T Electronic Imaging 2026.
2026.01 Started my Master's thesis on illumination-invariant intrinsic image decomposition at the University of Amsterdam, with industry partner 3DUniversum.
2025.06 Joined DXOMARK (Paris) as a Machine Learning Intern, adapting vision-language quality models to score portrait noise and texture.
2024.08 Admitted 1st of 198 applicants to the Erasmus Mundus COSI programme, studying at NTNU (Norway), Université Jean Monnet (France), and the University of Eastern Finland.
Earlier news
2023.10 Joined Vitex Software as an AI Engineer, building PlanZ, a multi-agent event-planning assistant.
2022.12 Graduated from SUNY Oswego with a BSc in Computer Science, Summa Cum Laude, GPA 3.81 / 4.0. Largely self-taught in AI alongside the degree.
2019.01 Admitted to SUNY Oswego with the Destination Oswego Scholarship and Merit Scholarship, my first step out of Vietnam.
2017.09 Admitted to National Economics University (Vietnam), one of the country's most selective universities, with an entrance score of 27.25 / 30.
A coat-rack scene from the Multi-Illumination Dataset, split diagonally: the dark input photograph on the right and the albedo the model recovers from it on the left, brighter and evenly lit
Luminance Constancy in Intrinsic Image Decomposition via Cross-Illumination Albedo Invariance

Trains on real photographs of one scene under different lighting so the recovered albedo keeps its luminance when the light changes: 28–39% less luminance variation in matched ablations and 7–14% lower albedo error on unseen coloured-light renderings, with 18.5M trained parameters. The next stage extends it to colour.

Research project  ·  from MSc thesis  ·  2026
Two versions of one portrait from the paper's Figure 1: more texture and more noise on the left, less noise and less texture on the right
 Best Student Paper — IS&T Electronic Imaging 2026
Adapting DeQA-Score for Attribute-Specific Portrait Quality Assessment

Co-authored at DXOMARK. Adapted a vision-language quality model to score portrait noise and texture separately, reaching SRCC 0.91/0.93 against expert ratings.

PlanZ landing page
Production AI at Vitex: PlanZ and a handwritten-form OCR pipeline

A multi-agent assistant serving hundreds of requests a day, with the failure rate cut from about 15% to about 5%. A Qwen3-VL-8B pipeline that extracts 14 fields from handwritten Japanese forms at 2,000 images an hour.

AI Engineer  ·  2023–2025
All research →    All projects →

Basketball, baking, and photos from 12 countries.

My story →    Gallery →