Open to opportunities

Tuan Luong

@tuanluong2

Message

Senior machine learning engineer building production AI systems from data pipelines to GPU/NPU deployment.

Vietnam

Message

What I'm looking for

I’m looking to build and scale production AI systems—end-to-end ML lifecycle, MLOps, and GPU/NPU deployment—where agentic LLMs, personalization, and computer vision can ship reliably and be monitored in production.

I’ve built and maintained production AI platforms for retail, fintech, agriculture, and insurance, including an agentic AI assistant for retail category management with a FastAPI backend (sessions, threads, chat proxy, and an EDP facade). I’ve also maintained a multi-model personalization engine for Watsons e-commerce, tuning serving latency with Redis caching, async processing, and Azure Cosmos DB.

In recent roles, I led multi-agent systems that decompose tasks with routing and output validation to reduce hallucinations, and I shipped an end-to-end SQL agent chatbot that analyzes natural language, auto-generates/corrects SQL, and streams results in real time. I manage the ML lifecycle end to end—data pipelines, training, MLOps, production monitoring, and quality gates.

Experience

Work history, roles, and key accomplishments

Current

Senior Machine Learning Engineer

Current

EPAM Vietnam

Oct 2025 - Present (10 months)

Built and maintained FastAPI backend for an agentic AI platform digitizing category management workflows. Designed multi-agent task decomposition with sub-agent routing and output validation.

OpenAI LangGraph Langsmith Langfuse MCP fastAPI

Lead AI Engineer

FPT Software

Apr 2025 - Oct 2025 (6 months)

Led and architected multiple concurrent AI engagements across fintech, real estate, insurance, and edge AI. Developed SQL Agent Chatbot, Automated Deed Classification, AI Slide/Videos Generation Platform, Cat Re-ID, and AI-powered Insurance Platform.

LangGraph Langsmith Azure OpenAI MSSQL fastAPI BERT AWS OpenAI API Docker PyTorch Ultralytics YOLO OpenCV Azure AI Search

Senior AI Engineer

Saigon Technology

Apr 2024 - Feb 2025 (10 months)

Led development of an AI camera system for crop monitoring, object detection, and anomaly alerts. Architected microservices AI APIs with Kafka and deployed models with TensorRT on Triton Inference Server.

fastAPI Kafka Triton YOLOv9 TensorRT PyTorch Talking Face Generation

Senior AI Engineer

FTECH

Apr 2023 - Apr 2024 (1 year)

Researched and developed an AI Generate Video Tool for lecture and sports news content. Designed AI Tool API in microservices architecture for multi-GPU deployment.

Python Kafka Prometheus fastAPI Minio DVC TensorFlow PyTorch

Senior AI Engineer

Asilla

Aug 2020 - Mar 2023 (2 years 7 months)

Developed AI algorithms for video analysis, highlight extraction, and emotion detection. Led Human Action Classification and pose-estimation systems for factory staff monitoring.

Flask PyTorch TensorRT OpenCV MySQL Docker DVC GitHub Actions MLFlow

AI Engineer

NeoLab

Jul 2018 - Jun 2020 (1 year 11 months)

Improved face recognition accuracy and performance; deployed on Jetson Nano/Xavier with TensorRT. Built real-time face recognition microservices and shopping mall analytics.

Python TensorFlow PyTorch Redis Flask OpenCV TensorRT NLP

Python Software Engineer

FUJITSU

Jun 2016 - Jun 2018 (2 years)

Developed OpenStack features and Cloud Operation System components. Implemented iRMC UEFI secure boot and BIOS configuration in Ironic bare-metal provisioning.

Python OpenStack Ironic