Situation professionnelle
Souhait professionnel
- Télécommunications
- INRIA
Résumé
I hold a deep personal interest in Reinforcement Learning (RL) and Large Language Models (LLMs). During my thesis, I gained a theoretical understanding of RL through my study of multi-armed bandit problems, progressing from fundamental to advanced configurations. Building on this foundation, my previous role allows me to expand my expertise into other areas of Artificial Intelligence such as Computer Vision, Speech Processing, and LLMs. I am an active contributor to the open-source community, currently maintaining and administering four PyPI packages: 1) tror-yong-asr, 2) tror-yong-ocr, 3) tror-yong-lm, and 4) neo-whisper. In addition, I manage a YouTube channel, KrorngAI, dedicated to educating Cambodian students on developing AI technology.
Expériences professionnelles
Chief technology officer
AI FARM ROBOTICS
De Novembre 2023 à Août 2025
Government official
Ministry of Industry, Science, Technology & Innovation (MISTI)
De Avril 2023 à Novembre 2023
Phd student
INRIA
De Octobre 2019 à Avril 2023
Intern
INRIA
De Avril 2019 à Août 2019
Reinforcement Learning for Markovian Bandits - I am working on bandit process problem in which the Markov chain is unknown and be learnt by the agent. The Gittins Index Policy is optimal for Restful bandit process and is being investigated. In Restless bandit process, Whittle's Index is asymptotically optimal and will be investigated for the extension of the problem.
Intern
RESEAU DE TRANSPORT D'ELECTRICITE
De Mars 2018 à Août 2018
Working on research problem : implementing Reinforcement Learning algorithms to control Power Network.
Intern
Ontruck AI Tech
De Juin 2017 à Septembre 2017
Implementing existing algorithms to solve Multi-Vehicle Routing Problem with Pick-up and Drop-off, and Time Window.
Associations
Parcours officiels
Langues
Khmer - Bilingue
Anglais - Courant
Français - Courant
linkedin