Skip to content
View tyc30827's full-sized avatar

Block or report tyc30827

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
tyc30827/README.md

πŸš€ Senior Data Engineer | MLOps & GenAI Specialist (Taiwan)

I am a highly motivated Senior Data Engineer specializing in MLOps and Generative AI (GenAI) application development, with 5-6 years of professional experience. I focus on designing, building, and deploying highly reliable and scalable data and machine learning platforms.

My expertise is anchored by published, cutting-edge research, including a First-Authored Publication in the Top-Tier Computer Science Journal, Information Fusion. My recent professional work centers on delivering advanced RAG systems and automated AI-labeling solutions in production environments. I champion robust MLOps practices to ensure efficient AI application lifecycle management and drive measurable business value.

πŸ’‘ Key Impact & Expertise

  • Groundbreaking Academic Achievement: First Author of an article on an Attentive Gated Graph Sequence Neural Network for financial trading, published in the Top-Tier Computer Science Journal, Information Fusion.
  • GenAI/LLM System Development: Successfully designed and deployed multi-modal RAG and structured data RAG solutions. Developed a cost-effective structured data RAG using DuckDB and Gemini-2.5-flash-lite.
  • Production MLOps: Built an end-to-end, automated AI-labeling system by integrating LLM (AWS Bedrock, PydanticAI) with Flask, Apache Kafka, and Dagster. The system's output is actively used in production recommendation and search engines.
  • Data Platform Leadership: Led the architecture optimization for Google BigQuery, resulting in a 90% reduction in query costs. Served as Code Owner for the BI codebase and mentored Junior Engineers.
  • Deep Learning Systems: Developed a deep learning-based Personalized Recommendation System (achieving 11.2%+ lift over baseline) and a GNN-based user preference system.

βš™οΈ Technical Stack (Focused on Production)

Category Core Expertise & Tools
GenAI / RAG / LLM AWS Bedrock (Knowledge Bases), LlamaIndex, PydanticAI, Huggingface, MLflow (GenAI Tracking)
MLOps & Lifecycle MLflow, Databricks, SageMaker, Docker, CI/CD, uv / poetry
Data Orchestration Dagster, Airflow, Airbyte, dbt (SQL)
Data Storage & DB BigQuery (Optimization), DuckDB, MongoDB (Document DB), PostgreSQL, AWS S3, AWS Neptune (Graph DB)
Cloud & IaC AWS (S3, EC2, Kinesis, Personalize, Rekognition), Terraform, Git
Programming Python (Core), SQL, PySpark, Flask / FastAPI (API), Gremlin
ML Models GNN, Deep Learning-based Recommendation Systems, Financial Time-Series, PyTorch, Keras

Pinned Loading

  1. data-science data-science Public

    Forked from ossu/data-science

    πŸ“Š Path to a free self-taught education in Data Science!

  2. machine-learning-systems-design machine-learning-systems-design Public

    Forked from chiphuyen/machine-learning-systems-design

    A booklet on machine learning systems design with exercises. NOT the repo for the book "Designing Machine Learning Systems"

    HTML