C

Clay Liang

AI & Data Science Professional

About Me

Passionate about building intelligent systems that make a difference

3+
Years Experience
10+
Projects Completed
92%
Model Accuracy
2
Universities

I'm a dedicated AI and Data Science professional currently pursuing my Bachelor's degree across two prestigious institutions: Leiden University and Tianjin Normal University. With hands-on experience at industry leaders like Airbus and Lenovo, I specialize in developing cutting-edge machine learning solutions.


My passion lies in leveraging artificial intelligence to solve complex real-world problems. From developing deep learning models for speech recognition at Tsinghua University to optimizing data pipelines at Airbus, I bring a unique blend of academic rigor and practical experience to every project.


Currently, I'm focused on Large Language Models, MLOps, and cloud-based AI solutions. I believe in the power of data-driven decision making and am committed to building scalable, efficient AI systems that drive business value.

Professional Experience

Building AI solutions at leading companies

Data Analyst Intern

Airbus - Tianjin, China
June 2025 - Present
  • Analyzed operational data to develop decarbonization metrics for sustainability initiatives
  • Designed and implemented Databricks pipelines processing 10TB+ aviation datasets
  • Created interactive dashboards for executive decision-making using Power BI
  • Reduced data processing time by 40% through pipeline optimization
  • Collaborated with cross-functional teams to identify optimization opportunities

Data Science Intern

Lenovo - Tianjin, China
February 2025 - June 2025
  • Designed comprehensive dashboards in Tableau and Power BI for supply chain optimization
  • Developed data optimization strategies improving query performance by 25%
  • Led team of 5 interns in implementing automated reporting systems
  • Conducted statistical analysis on customer behavior patterns
  • Presented insights to senior management influencing key business decisions

Research Assistant

Tsinghua University - Remote
2024 - 2025
  • Developed deep learning models for audio/speech recognition achieving 92% accuracy
  • Improved model performance by 15% through advanced loss function tuning
  • Optimized backend runtime reducing inference time by 30%
  • Built interactive visual dashboards for model performance monitoring
  • Published research findings in university technical reports

Featured Projects

Innovative solutions powered by AI

🎥

Video Annotator Tool

Flask-based web application for efficient video labeling and annotation. Features frame-by-frame navigation, multi-class labeling, and batch processing capabilities. Used by 20+ researchers for creating ML training datasets.

Python Flask OpenCV JavaScript SQLite
🎤

Speech Recognition System

End-to-end speech recognition system using Transformer architecture. Achieved 89% word error rate on custom dataset with real-time transcription and streaming capability.

PyTorch Whisper ONNX FastAPI Docker
⚙️

Predictive Maintenance Dashboard

ML-powered dashboard for industrial equipment maintenance prediction. Reduced unplanned downtime by 35% in pilot implementation. Won first place in University AI Hackathon 2024.

Python Scikit-learn Streamlit PostgreSQL XGBoost
📊

Customer Behavior Analytics

Comprehensive analytics platform for understanding customer behavior patterns. Implemented clustering algorithms and predictive models to improve customer retention by 20%.

Python Pandas Plotly Apache Spark AWS
🤖

LLM Fine-tuning Framework

Developed a framework for fine-tuning large language models on custom datasets. Includes automatic prompt engineering and evaluation metrics.

Transformers PyTorch Hugging Face PEFT Gradio
☁️

Cloud ML Pipeline

Scalable machine learning pipeline on AWS for automated model training, evaluation, and deployment. Handles 1M+ predictions daily with sub-100ms latency.

AWS SageMaker Lambda S3 Docker Kubernetes

Technical Skills

Technologies I work with

Programming Languages

Python SQL Java C++ JavaScript R

ML/DL Frameworks

PyTorch TensorFlow Scikit-learn Keras Hugging Face XGBoost

Data Tools

Databricks Apache Spark Pandas NumPy Docker Git

Visualization

Tableau Power BI Matplotlib Seaborn Plotly D3.js

Cloud Platforms

AWS Google Cloud Azure SageMaker Lambda EC2

Databases

PostgreSQL MySQL MongoDB Redis Elasticsearch SQLite

Achievements & Certifications

Recognition and continuous learning

🏆

1st Place - AI Hackathon

University AI Hackathon 2024 - Predictive Maintenance Solution

📜

AWS ML Specialty

AWS Certified Machine Learning - Specialty (In Progress)

🎓

Deep Learning Specialization

Coursera - Andrew Ng's Deep Learning Course

📊

Google Data Analytics

Google Data Analytics Professional Certificate

🏅

Top 10% Kaggle

House Prices Prediction Competition

☁️

Azure Fundamentals

Microsoft Azure Fundamentals (AZ-900)

Get In Touch

Let's discuss how we can work together

Contact Information

Leiden, South Netherlands

Send Message