I’m building toward an AI / Machine Learning Engineer path with a strong interest in:

• Generative AI & Agentic Frameworks (OpenClaw)
• Model Context Protocol (MCP) & Tool Calling
• Deep Learning
• RAG systems
• MLOps and deployment
• production-ready AI workflows
• HarmonyOS & Mobile Development (ArkTS)

I like turning theory into projects that are not just experimental, but structured, reproducible, and deployable.

Right now, I’m focused on growing across three layers:

• machine learning fundamentals
• model evaluation and tuning
• representation learning
• deep learning architectures
• Apple Silicon ML optimization (MLX, Create ML)

• prompt workflows
• retrieval-augmented generation (RAG)
• autonomous AI agents (OpenClaw, Devin)
• local LLM deployment & testing (LM Studio)
• context & tool integration (Model Context Protocol - MCP)
• fine-tuning foundations
• LLM application design
• evaluation and iteration

• Git / GitHub workflows
• Linux and shell scripting
• Docker and containers
• CI/CD thinking
• cloud optimization, resilience, and performance
• cross-platform and OS-level development (ArkTS, OpenHarmony)

I’m shaping my profile around:

• AI application & autonomous agent development (OpenClaw, Devin)
• GenAI-powered systems & local LLM integration (LM Studio)
• deep learning experimentation (PyTorch, MLX)
• extending AI capabilities with external tools (MCP)
• model evaluation and optimization
• deployment-minded engineering
• cross-platform ecosystem integrations (ArkTS)
• end-to-end project execution

My goal is to become someone who can:

design, build, evaluate, and ship practical AI systems end-to-end

My recent learning path includes topics such as:

• Applied Generative AI
• Advanced RAG Implementation
• Foundation Models & Fine-Tuning
• Machine Learning
• Deep Learning
• Model Tuning and Evaluation
• Docker / Containers
• Linux / Shell
• Git & GitHub
• CI/CD and MLOps
• Cloud cost / performance / resilience

I’m not just collecting certificates — I’m using them to build stronger projects and a clearer engineering direction.

I’ll update this section as I refine and pin my best repositories.

• Gõ Tiếng Việt - HarmonyOS Keyboard A Vietnamese Input Method (Telex) for HarmonyOS / OpenHarmony built with ArkTS, supporting custom UI, clipboard management, and Python-based auto-patching scripts.

• EEG Abnormally Detection Experimenting with training, architecture choices, and performance analysis for anomaly detection in EEG data.

• Machine Learning Specialization Solutions and notes for the Machine Learning Specialization, working on data preparation, feature engineering, modeling, and interpretation.

• DevOps & CI/CD Projects Turning code into reproducible, containerized, deployment-ready systems. Includes RESTful API microservices with automated testing using TDD, BDD, Flask, and Behave (TDD/BDD Project).

• Deep Learning for Computer Vision Exploring deep learning architectures and computer vision applications.

• GitHub: github.com/ur77ec17235
• Coursera: IBM RAG and Agentic AI Professional Certificate, IBM DevOps and Software Engineering
• LinkedIn: add when ready
• Kaggle: XiangFang24

Learn deeply. Build practically. Ship thoughtfully.