Resume

Click here to download the PDF version of my resume.

Work Experience

• AI Solutions Consultant and AI Engineer
  iApp Technology Limited, Thailand, Jan 2024 - Apr 2024
  • Contributed to strategic decision-making, guiding AI project lifecycles from concept to completion, aligning with trends and goals to ensure top-quality and performance for successful delivery to clients.
  • Provided expert consultation on integrating AI solutions to client products for enhancing their business and achieving strategic goals.
  • Spearheaded POCs, developed, and delivered AI solutions, leveraging open-source LLMs (e.g., LLaMa-2 and OpenThaiGPT) with RAG through PyTorch and llama.cpp, for various use cases, including, financial agents, helpdesk, and information retrieval tasks.
  • Conducted comprehensive data analysis and modeling using PyTorch, enhancing model accuracy by up to 27% for various tasks such as intent classification, sentiment analysis, and face-shape classification.
  • Contributed the development of state-of-the-art AI products for various domain solutions, e.g., multilingual ASR (English, Japanese, Chinese and Thai) with up to 99% of accuracy achievement and LLM-based FAQ classification with 88.97% of accuracy.
• Machine Learning Researcher and Lecturer
  Artificial Intelligence Association of Thailand, Thailand, Jan 2018 - Aug 2023
  • Designed and delivered Python courses on data analysis, AI, and ML. Covered tools (e.g., pandas, scikit-learn, spacy) and algorithms (e.g., regression, SVM, neural nets) in text and image analysis to educate hundreds of students, cultivating ML enthusiasts in Thailand.
  • Offered in-depth consultations to undergraduate and graduate students on theoretical, practical, ML concepts, strategically guiding study plans and assisting in the publication of over 20+ international research papers and projects.
• Research Assistant
  Tokyo Institute of Technology, Japan, Sep 2019 - Mar 2020
  • Collaborated with a multidisciplinary team of 8 members to design and implement tailored APIs for Natural Langue Understanding and Generation units for Japanese conversational dialogs.
  • Designed, developed, and applied LSTM-based sequence-to-sequence models using PyTorch for text generation and refinement, resulting in enhanced fluency and a more natural linguistic output, validated through human evaluations.
• Machine Learning Engineer, Software Engineer, and Researcher
  iApp Technology Limited, Thailand, Mar 2017 - Feb 2018
  • Spearheaded and led a cross-disciplinary team of linguists and software developers to construct the first Thai Treebank, comprising over 5,000 entries, contributing Thai NLP resources, enhancing research, innovations, and applications in the NLP community.
  • Led the development and deployment of native and web applications in React, Python, and GCP as a pipeline product for syntactic extraction, with an emphasis on intuitive UX, bolstering ongoing developments in the Thai NLP community.

Selected Projects

• Extreme Fine-tuning: A Novel and Fast Fine-tuning Approach for Text Classification (EACL 2024) (Mar 2024)
  • Proposed a novel text classification fine-tuning approach incorporating backpropagation with extreme learning machine, reducing fine-tuning time while retaining classification accuracy and F1-score.
  • Attained faster fine-tuning time by up to 74.8% with comparable scores over recent state-of-the-art models on MELD, IEMOCAP, IMDb, and AG News datasets.
• LLaVAC: Fine-tuning LLaVA as a Multimodal Sentiment Classifier (Jan 2024)
  • Proposed a method to fine-tune Large Language-and-Vision Assistant (LLaVA) as a classifier for classifying multimodal sentiment labels by designing a prompt to consider unimodal and multimodal labels and generating predicted labels.
  • Outperformed state-of-the-art baselines by up to 7.31% in accuracy and by 8.76% in weighted-F1 in the MVSA-Single dataset.
• A Unification-based Knowledge Graph Construction for Thai Profile Generation from Online Resources (Sep 2023)
  • Constructed a knowledge graph for Thai researchers, using 6+ million entries crawled from online research databases.
  • Designed a semi-supervised method with multi-task learning to extract entities/relations, improving F1-score by 8% over baseline.
• Simple2In1:A Simple Method for Fusing Two Sequences from Different Captioning Systemsinto One Sequence (Sep 2023)
  • Developed a T5-based generative model for Thai captions fusion, outperforming baselines by 5.2% in sBLEU and ROUGE-L scores.
  • Accomplished a sBLEU score of 79% and a ROUGE-L score of 90% for a small captioning dataset comprising 3,168 samples.
• LATTE: Lattice ATTentive Encoding for Character-based Word Segmentation (Jun 2023)
  • Proposed, and implemented a sequence labelling method that integrates multi-granularity linguistic units, Lattices, GNNs, PTMs, and Attention Mechanism using PyTorch and PyG to generate and refine text representations for word segmentation.
  • Achieved state-of-the-art performance (97.7% to 99.4% of F1-score) across Asian languages: Japanese, Chinese, and Thai.
• Multimodal Sentiment Analysis Using Multiple Labels from Different Modalities (Mar 2023)
  • Collaborated with students to design and implement a sentiment analysis model for social network data, leveraging text, image, and multimodal labels using CLIP, BERT, and RoBERTa. Yielded up to 2% improvement in F1-score over recent models.
  • Attained F1-scores of 74.1% for MVSA-single and 62.0% MVSA-multiple datasets.
• Detecting Fraud Job Recruitment Using Features Reflecting from Real-world Knowledge of Fraud (Mar 2022)
  • Developed a method to classify fake job recruitments using a set of novel features designed to reflect fraudster behaviors.
  • Yielded accuracy of 97.64% for Employment Scam Aegean Dataset (EMSCAD).
• Public Budget Usage Monitoring System (Feb 2019)
  • Cooperated with an interdisciplinary team to develop a monitoring system that utilizes Scrapy to crawl large-scale unstructured data from government sites, such as procurement and budget portals, for corruption detection in text data. Deployed by two organizations.
  • Developed a text classification method in TensorFlow, with rule-based enhancements, for corruption detection, validated by experts.
  • Obtained Bronze Medal in The 47th International Exhibition of Inventions Geneva

Education

• Doctor of Engineering, Tokyo Institute of Technology, Japan, 2019 - 2023
  • Major: Information and Communications Engineering
  • Advisor: Prof. Manabu Okumura
  • Thesis: Incorporating Multi-granularity Linguistic Units in Character-based Word Segmentation
  • Scholarship: NSK Foundation Scholarship
• Master of Engineering, Sirindhorn International Institute of Technology, Thammasat University, Thailand, 2015 - 2018
  • Major: Information and Communication Technology for Embedded Systems
  • Advisor: Prof. Thanaruk Threeramunkong
  • Thesis: A Framework of Thai Treebank Construction and Grammar Refinement
  • Scholarship: TAIST - Tokyo Tech Scholarship
• Bachelor of Science, Thammasat University, Thailand, 2011 - 2015
  • Major: Computer Science
  • Advisor: Dr. Ratchata Peachavanish
  • Thesis: Web Application for Learning Thai Language using Song Lyrics
  • Activity: President of Computer Science, Faculty of Science, Thammasat University

Skills

• Technical Skills
  • Programming Languages: Python, C/C++, Rust, Java
  • ML Toolkits: PyTorch/Lightning, TensorFlow/Keras, Hugging Face, PyG, DGL, OpenCV, Scikit-learn, Spacy, NLTK
  • Tools & Technology: Linux, Hadoop, Spark, SQL, NoSQL, Oracle Database, Docker, Jupyter, Neo4j, Elasticsearch, GCP, AWS, Git
• Languages
  • Thai: Native
  • English: Professional working proficiency
  • Japanese: Limited working proficiency