Machine Learning Developer

Ati Tesakulsiri

Computer Vision, Video Analytics, Multimodal AI, and Applied ML

Address:
Nonthaburi, Thailand
Nationality:
Thai
Phone:
095 787 5141 / (+66) 95 787 5141
Portrait of Ati Tesakulsiri

Working Experience

Asian Institute of Technology, Pathumthani, Thailand

AI Center Unit

  • Machine Learning Developer - Full time, current position
  • Software Developer - Full time, after graduation
  • Graduate Research Assistant - Internship

Selected Work Projects

  • Text-Based Video Smart Search

    Developing a Thai-language surveillance video search PoC using generative AI, on-premise LLM serving, vision-language multimodal models, fine-tuning, and vector database integration.

  • CCTV Black Smoke Measurement and Evaluation

    Developed research software and a web app with video analytics for vehicle black-smoke detection, screening, and multi-frame emissions analysis with ENTEC, NSTDA.

  • Safety AI PoC

    Developing tollway surveillance analytics for wrong-way driving, speeding, illegal parking, unexpected objects, 300-meter falling-object detection, and vehicle length classification.

  • AI Service for Video Analytics

    Contributed to AI service development, model training, optimization, hosting tests, CI pipeline upgrades, automated tests, reporting, and service software patching.

  • Face Recognition

    Owned analytics-side face recognition covering detection, tracking, recognition integration, evaluation, and deployment support.

  • Wildfire Simulation and Component Classification

    Developed wildfire component classification and segmentation from drone video, with forecasting support using empirical models and satellite data.

  • Video Action Recognition

    Improved action recognition post-processing to reduce fall detection false positives and evaluated system performance.

  • Other Demo Projects

    Built accident detection logic with tracked object-pair reasoning using Qwen 3.5, plus VLM-based scene detection for fire, violence, fall, smoke, and abnormal surveillance events.

Thesis

MULTI-MODAL PERSON RETRIEVAL: BRIDGING TEXT, IMAGES, AND RE-IDENTIFICATION

Developing a Transformer-based multimodal system integrating text and image encoders for identity processing, cross-camera person re-identification, and text-based person search in one OpenAI CLIP-inspired model.

Education

Asian Institute of Technology

M.Sc. Data Science and Artificial Intelligence, GPA 3.7/4.0

Hisamatsu Prize recipient. Courses include machine learning, data modeling, business intelligence, programming for data science and AI, and natural language understanding.

Suranaree University of Technology

Bachelor of Science, GPA 3.60/4.0

YSTP research scholar from NSTDA and full scholarship recipient from the university.

Certifications

  • CS50x

    Core programming and web application concepts with C, Python, and SQLite.

  • CS50AI

    Core concepts of artificial intelligence and machine learning.