I focus on LLM Agents, Artificial Intelligence, Computer Vision, and Multimodal AI Systems.
I am an LLM Agent engineer with a background in artificial intelligence and computer vision.
My current interests include:
- LLM Agent systems and workflow orchestration
- Tool use, function calling, RAG, and structured generation
- Multimodal large language models
- Computer vision, object detection, and pose estimation
- AIGC, including image and text generation
- Multimodal medical image segmentation and glioma classification
LLM Agents : Agent Workflow, Tool Calling, Function Calling, Dify, LangChain
RAG Systems : Retrieval, Reranking, Context Engineering, Structured Generation
AI Models : PyTorch, Transformers, Multimodal LLMs, Computer Vision, AIGC
Engineering : Python, C++, FastAPI, Docker, Linux, GitHub Actions
Deployment : API Integration, Model Serving, Workflow Automation
LLM Agents : Planning, tool use, workflow orchestration, structured output
RAG Systems : Retrieval, reranking, context compression, evidence-grounded generation
Computer Vision : Detection, segmentation, pose estimation, medical image analysis
AIGC : Image generation, text generation, multimodal content creation
Engineering : Python, C++, Linux, Docker, Git, model deployment
I am currently working on practical LLM Agent systems, multimodal AI applications, and engineering-oriented AI workflows.
My long-term interests include:
- Building reliable and controllable LLM Agent applications
- Improving structured generation and tool-calling reliability
- Combining multimodal understanding with real-world AI systems
- Deploying AI models into production-oriented workflows