Hi 👋 I am An Son
- AI engineer with 3+ experience working in AI. I have the ability to research, design, develop AI solutions, particularly in the field of Computer Vision, Natural Language Process, LLM.
- Designing and implementing deep learning models for object detection / object tracking, image recognition, medical imaging, and autonomous systems.
- Designing and developing chatbot, AI Agent in Retail, Healthcare.
- System architecture design, AI pipeline flow design, and database design for scalable AI applications.
- Working with large-scale datasets, ensuring high-quality data preprocessing and augmentation.
- Optimize model performance, improve AI model accuracy, and fine-tune algorithms to meet both technical and business requirements.
- Deploy AI models in production environments, ensure scalability, robustness, and efficiency for real-world applications.
| Operating System | MacOS, Windows (10/11), Ubuntu (20/22) |
| Program Language | Python |
| Computer Vision |
Tensorflow, Pytorch, Sklearn, YOLO, ONNX, NVIDIA TensorRT,... Image classification, Object detection, Object segmentation, Object tracking, OCR, Face recognition, Person behavior, Pose detection, Gaze recognition,... |
| LLM | LangChain, LangGraph, LangFlow, Prompting, RAG, Agent, MCP, A2A, VectorDB,... |
| MLOps | Docker, CI/CD, Microservice, Redis, Kafka, FastAPI, NVIDIA Triton Infer Server, Nvidia Deepstream,... |
| Cloud | AWS, Azure |
| Database | MongoDB, Qdrant, PostgreSQL |