About Me

Ho Tan Dat

AI Researcher & PhD Candidate

Download CV

AI Researcher and PhD candidate at the University of Debrecen on a fully funded Hungarian State scholarship. Building production AI systems from LLM inference and fine-tuning to multi-stage NLP pipelines, computer vision, and time-series forecasting. Bridging academic research with hands-on engineering across microservices architecture and full-stack development.

PhD in Informatics (Machine Learning / AI)
University of Debrecen
Feb 2026 - Present
Fully funded Cooperative Doctoral Scholarship financed by the Hungarian State
Master of Computer Science
Duy Tan University
Dec 2021 - Aug 2024
GPA: 3.53 / 4.0
Bachelor of Software Engineering (CMU)
Duy Tan University
Oct 2016 - May 2020
GPA: 3.67 / 4.0
AI Researcher
University of Debrecen
Jun 2025 - Present · Debrecen, Hungary
  • Built a multi-service compute and AI inference platform with microservices architecture (FastAPI, Nginx reverse proxy, Redis, MongoDB), serving as a unified research computing workspace
  • Designed and deployed an LLM inference service powered by vLLM with OpenAI-compatible API, supporting streaming chat completions, embeddings, and dynamic model load/unload management
  • Developed an AI text humanizer with a 3-stage NLP pipeline (paraphrasing, word perturbation, grammar correction) using a LoRA fine-tuned Qwen3-32B model, with parallel chunk processing and async job queue
  • Implemented a document extraction pipeline using Vision Language Models (VLM) to extract structured data from uploaded PDFs via asynchronous task workers
  • Developed time-series forecasting models (Temporal Fusion Transformer, DeepAR) for sales predictive analytics with weather and holiday effect integration
  • Designed a centralized API gateway with JWT authentication, per-service API key injection, and unified OpenAPI documentation aggregation
  • Produced research papers for publication in international conferences and journals
AI Engineer
Brightsource Data Analytics
Sep 2024 - Sep 2025 · Remote, Israel
  • Leveraging AI models (Transformers, BERT) to extract structured data from unstructured sources
  • Labeling and training custom AI models for task-specific resolutions
  • Developing modules that integrate LLM APIs for business requirements
  • Building RESTful APIs with FastAPI for scalable application architectures
  • Implemented embedding-based RAG solution combining semantic retrieval with generative AI
AI Engineer
NDC Tech
May 2022 - Sep 2024 · Da Nang, Vietnam
  • Integrated AI models into client systems (face recognition, vehicle plate recognition)
  • Developed RESTful APIs using FastAPI to integrate AI into web applications
  • Containerization, Kubernetes (K8s), and Google Cloud Platform (GCP) deployments
  • Established and validated hypotheses on training datasets for robust model performance
  • Participated in code reviews, sharing Python development best practices
Teaching Assistant, Lecturer & Researcher
Duy Tan University
Jun 2020 - May 2022 · Da Nang, Vietnam
Teaching Assistant
  • Assisted faculty in delivering Software Project Management, Software Testing, and Basic Programming courses
  • Facilitated lab sessions and provided hands-on support with coding assignments
Lecturer
  • Created and delivered course content aligned with current industry practices
  • Mentored students through academic journey, project work, and thesis development
Researcher
  • Conducted research in Machine Learning focusing on algorithm development and applications
  • Published research findings and presented at conferences
5 papers
In Submission
Grounded-SAM Plus: Enhancing Mask Quality for Image Dataset Augmentation through Diffusion-Based Refinement
2025
Multimedia Tools and Applications, Springer
Ho, D. T., Bérczes, T., & Nguyen, M. D.
In Submission
AI-Enhanced Grouped Time-Series Forecasting with Weather and Holiday Effects
2025
International Journal of Knowledge and Systems Science, IGI Global
Ho, T. D., Nguyen, M. D., & Bérczes, T. M.
In Submission
GymViet: AI-driven Fitness Assistance Platform
2025
IPMV 2025 Conference
Pham, D. D., Ho, V. N., Pham, M. T., et al.
In Submission
Leveraging YOLO Object Recognition for Enhanced Interactive English Vocabulary Learning in Children
2025
CITISIA Journal
Che, K. Q., Pham, H. T., Tran, B. D., et al.
In Submission
Machine Learning for Multi-Horizon Financial Ratio Forecasting
2025
Publisher TBD
Dat T. Ho, Anh M. V. Pham, & Bérczes, T. M.
4 papers
Applying AI Chatbot to Leverage the Quality of Tourism Information Systems Services
2022
Da Nang Publishing House
Nguyen, T. S., Doan, K. T., Phung, H., Pham, V. T., Ho, T. D., & Nguyen, D. M.
DSParking: Applying OpenCV and QR CODE for Building a Smart Parking Management System
2022
Da Nang Publishing House
Ho, T. D., Nguyen, H. T., Nguyen, T. B. N., et al.
ODWai: Object Detection on The Web Application Interface using Deep Learning
2021
Da Nang Publishing House
Nguyen, B. C., Nguyen, H. H., Pham, M. H., Le, V. T., Ho, T. D., & Nguyen, D. M.
Uberwasted: Reporting and Collecting Waste Using Location Based and Deep Learning Technologies
2020
International Conference on Future Data and Security Engineering, Springer Singapore
Nguyen, B. T., Tan, D. H., Dieu, H. V. T., Khac, D. N., & Dinh, H. T.
Technical Competencies
LLM Deployment & Fine-Tuning

Deployed and managed vLLM inference servers with OpenAI-compatible APIs, streaming completions, and dynamic model management. Fine-tuned large language models (Qwen3-32B) using LoRA adapters for domain-specific tasks

vLLM LoRA Qwen Transformers
NLP & Text Processing Pipelines

Built multi-stage NLP pipelines (paraphrasing, perturbation, grammar correction) with concurrent processing. Experienced with prompt engineering, embedding-based RAG solutions combining semantic retrieval with generative AI

NLP RAG BERT Embeddings
Computer Vision & VLM

Applied vision models for face recognition, vehicle plate recognition, and object detection (YOLO, Grounded-SAM). Built document extraction pipelines using Vision Language Models to parse structured data from PDFs

YOLO SAM VLM OpenCV
Time-Series Forecasting

Developed production forecasting models using Temporal Fusion Transformer and DeepAR for predictive analytics with weather and holiday effect integration across grouped time-series data

GluonTS TFT DeepAR
Microservices & API Architecture

Designed and built multi-service platforms with API gateway routing, JWT authentication, per-service key injection, async task queues (Redis/RQ), and unified OpenAPI documentation aggregation

FastAPI Redis MongoDB Nginx
GPU Computing & Infrastructure

Managed multi-GPU server environments for AI inference, built real-time monitoring dashboards, sandboxed code execution with GPU access, and process management via Supervisor/systemd

CUDA nvidia-smi Supervisor
DevOps & Cloud Deployment

Containerization with Docker, orchestration with Kubernetes, and cloud deployments on GCP. Experienced with Nginx reverse proxy configuration, CI/CD workflows, and production service management

Docker K8s GCP Git
Research & Academic Writing

Published and submitted papers in international conferences and journals (Springer, IGI Global). Skilled in identifying research gaps, synthesizing concepts, and translating findings into practical applications

Full-Stack Development

End-to-end application development from vanilla JS frontends to Python backends with MongoDB/Redis data layers. Deep understanding of the full software development life cycle

Python JavaScript ReactJS Figma
Soft Skills
Problem Solving
Presentation
Communication
Adaptability
Coaching Leadership
Change Management
TOEIC
940 / 990
2023
IELTS Academic
7.0 / 9.0
2021