cv
Basics
Name | Wong Wing Yan, Tracy |
Label | AI Engineer |
tracywong117@gmail.com | |
Phone | +852 5118 4098 |
Url | https://github.com/tracywong117 |
Summary | AI Engineer skilled in deep learning, data engineering, and scalable systems. Experienced in building advanced sequence embedding models, semantic search platforms, and distributed data pipelines for large-scale biological datasets. |
Work
-
2023.07 - Present AI Programmer
D24H
Developed and deployed advanced deep learning and data engineering solutions at scale for biological data.
- Developed advanced sequence embedding models with Transformers, triplet/ladder loss, and binarization techniques.
- Optimized models with C++ modules (Pybind11) and distributed training (DDP).
- Built a semantic search platform for 30M+ NCBI SRA records using PostgreSQL, pgVector, and custom embeddings.
- LLM-driven data cleaning and text-to-SQL workflow improvements.
- Implemented distributed model inference pipelines using Hadoop, Spark, and HDFS for >2TB vector data.
- Enabled rapid retrieval with FAISS and advanced data structures (Binary Relation Wavelet Tree, SDSL).
- Used RocksDB and PostgreSQL for scalable, high-performance data management.
- Extended C++ library functions and independently configured/build the codebase.
- Designed and deployed interactive data visualization dashboards with Vue.js, TailwindCSS, Chart.js, and Plotly.js.
-
2022.06 - 2023.05 AI Engineer (Intern)
InnoBlock Technology Limited
Worked on computer vision and security monitoring systems for government agencies.
- Fine-tuned custom object detection models using YOLO.
- Designed real-time person tracking algorithms across camera streams.
- Integrated facial recognition, object detection, and tracking into a data security monitoring platform.
Education
-
2019.09 - 2023.05 Hong Kong
Awards
- 2019.09.01
Faculty of Engineering Admission Scholarship
The Chinese University of Hong Kong
- 2022.09.01
Shaw College GE Scholarship
Shaw College, CUHK
Skills
Programming Languages | |
Python | |
C/C++ | |
JavaScript | |
SQL |
AI & Data Science Libraries | |
PyTorch | |
Scikit-learn | |
Huggingface | |
SpaCy | |
OpenCV | |
YOLO | |
Pandas | |
Matplotlib |
Data Engineering & Distributed Systems | |
Spark | |
Hadoop | |
HDFS | |
PostgreSQL | |
FAISS | |
RocksDB |
Frontend & Visualization | |
Vue.js | |
TailwindCSS | |
Chart.js | |
Plotly.js | |
D3.js |
Cloud Platforms | |
AWS EC2 | |
AWS S3 | |
Azure | |
OpenAI | |
GCP | |
Vertex AI | |
GCP BigQuery | |
GCP OAuth |
Tools & DevOps | |
Docker | |
Git | |
Nginx | |
CMake | |
GitHub Actions | |
GitHub Copilot |
Languages
Cantonese | |
Native |
English | |
Fluent |
Mandarin | |
Fluent |
Interests
AI Research | |
Deep Learning | |
Semantic Search | |
Computer Vision | |
Natural Language Processing | |
Distributed Systems | |
Data Engineering |