Ati Tesakulsiri Address: Nonthaburi, Thailand Nationality: Thai Personal mail: tesakulsiriati@gmail.com Phone number (Thai / International call): 095 787 5141 / (+66) 95 787 5141 Personal site: https://atichetsurakul.github.io/ LinkedIn: https://www.linkedin.com/in/ati-tesakulsiri-1a8409263/ Skills Language: Python Tools/ Frameworks: Claude code, Codex, Pytorch, Ultralytics, Huggingface, Triton Inference Server, Docker, GitLab-CI/CD Theory: Machine Learning, Deep Learning, Image and Video processing, Signal processing, Natural language processing, Data science Environment/ Operation system: Ubuntu Selected Projects Work Project Text-Based in video smart search: Developing a PoC system, by utilizing generative AI for surveillance recorded search engine with Thai language. Leveraged LLM-based text manipulation tools (LangChain, SmolAgent, Ollama) for on-premise LLM serving; developed vision-language multimodal systems with on-premise serving and fine-tuned models, integrated with vector databases to support with any video analytics program. CCTV Black Smoke Measurement and Evaluation: Developed research software to detect and analyze black smoke from vehicles. Collaborated with ENTEC (NSTDA) as an AI and software developer. Built a web application equipped with video analytics for smoke screening and multi-frame analysis of emissions from light-duty diesel trucks and vans. Safety AI POC: Developing a PoC system for tollway surveillance that detects abnormal driving behaviors—including wrong-way driving, speeding, illegal parking, and unexpected object presence. Responsible for building a zoom-assisted API capable of detecting falling objects on the road at distances up to 300 meters and vehicle length classification. AI service for video analytics: Contribute in certain tasks in AI service, AI training, optimizing and hosting tests, on specific groups of tasks. Upgrading the CI pipeline of the repositories for automatic unit test, evaluation test, reporting, and patching a new version of the service software. Face recognition: Owned the analytics-side face recognition system, including 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 performed system performance evaluation. Other demo project: Developed accident detection demo logic using tracked object pair information and Qwen 3.5 for reasoning over vehicle interactions. Built VLM-based scene detection for fire, violence, fall, smoke, and abnormal surveillance events. Contributed to AI service development, AI training, optimization, hosting tests, CI pipeline upgrades, automated unit/evaluation testing, reporting, and service patching. University and Personal Project Joules of Saim: Designed and built an end-to-end business intelligence project to forecast electricity prices. Responsible for some part of the data pipeline: gathering data from multiple APIs (BOT, EGAT), training a time-series forecasting model, and deploying an interactive Python-based web dashboard. Diabete classification using Raman spectrums: Applied traditional machine learning (SVM, ANN) and signal processing techniques to classify diabetes from Raman spectrums, indicating a strong foundation in data science fundamentals. Bros of Rainbow: Conducted a comparative analysis of reinforcement learning architectures (Rainbow, DDQN, LSTM, Transformer variants) for game-playing agents in OpenAI Gym. Systematically evaluated the impact of model design on learning efficiency and performance. NLP application: Developed and hosted a web application showcasing multiple NLP models, including a resume parser (NER), sequence-to-sequence machine translation, and text generation, demonstrating an understanding of deploying diverse NLP tasks. Serotonin Extraction and quantitative analysis: Studied a substance absorption with monolith material approach for urine extraction to perform quantitative analysis of serotonin concentration that involves depression. Thesis: MULTI-MODAL PERSON RETRIEVAL: BRIDGING TEXT, IMAGES, AND RE-IDENTIFICATION Developing a Transformer-based multimodal system integrating a text encoder and an image encoder for person-related tasks, including identity information processing, cross-camera person re-identification, and text-based person search all in one model (openAI CLIP design). Working Experience Asian Institute of Technology, Pathumthani, Thailand June 2023 - Present Machine Learning Developer, AI Center Unit (Full time) (Current Position) Software Developer, AI Center Unit (Full time) (After Graduate) Graduate Research Assistance, AI Center Unit (Intern) Education Asian Institute of Technology, Thailand Graduate in May 2024 Master of Science in Data Science and Artificial Intelligence. (GPA: 3.7/4.0). Recipient of the Hisamatsu prize. Course taken: Recent Trends in Machine Learning, Data Modeling and Management, Machine Learning, Business Intelligence and Analytics, Computer Programming for Data Science and Artificial Intelligence, Natural Language Understanding Suranaree University of Technology, Thailand Graduate in January 2021 Bachelor of science (GPA: 3.60/4.0). YSTP research scholar from NSTDA and full scholar from University Scholarships & Awards Hisamatsu Prize (Ranked #1 in Batch Academic Record): Granted by Asian Institute of Technology Young Scientist and Technologist Program: Granted by National Science and Technology Development Agency Royal Thai Government Fellowships (100%) Scholarship: Granted by Asian Institute of Technology Talented individuals in science and technology Scholarship: Granted by Suranaree University of Technology for Full scholarship for bachelor's degree Certifications CS50X Certificate link Core programming, and web application concept with c, python and sqlite study before Master degree study. CS50AI Certificate link Core concept of fundamental Artificial Intelligent and Machine Learning for Master degree study.