Hello! Welcome to my GitHub. I'm Henry, a machine learning engineer with a passion in knowledge graphs, GenAI, and cloud engineering solutions. I am currently purusing a Master's degree at Northwestern University.

A personal project that builds an encoder-decoder transformer from scratch. It includes logic for word embedding, positional encoding, self attention, and encoder-decoder attention.

A collaborative project with the Center for Deep Learning at Northwestern University that involved the design, implementation, and maintancence of an IoT streaming data prediction pipeline for three different usecases on AWS.

A modular and configurable machine learning pipeline designed to classify cloud types from images. The pipeline can be run locally or inside a docker container, and can save artifacts from the process to anywhere you want.

• Machine Learning Engineer Intern, Amazon (Current)
  • Developing a system using LLMs to explain differences in knowledge graph snapshots.
• Data Science Intern, Roblox
  • Created a diagnostic framework by predicting the probability of extreme impression changes and identifying important contributing factors.
• Machine Learning Engineer Intern, Center for Deep Learning
  • Built AWS IoT real-time streaming pipelines and automated model retraining processes.

• Languages: Python, R, Java, JavaScript
• ML / AI: PyTorch, TensorFlow, OpenCV, LangChain, ChatGPT
• Big Data: Spark, SQL, Hadoop, Hive, Trino, MapReduce, Neo4j/Cypher, Tableau
• Tools: AWS, Linux/Unix, Docker, Git/GitHub, Excel

• Master of Science in Machine Learning and Data Science
  • Northwestern University, McCormick School of Engineering
• Bachelor of Science in Applied Mathematics, Bachelor of Science in Statistics
  • UCLA, College of Letters and Science

• Email: [email protected]
• LinkedIn: linkedin.com/in/henryliang8/

Feel free to explore my repositories to see the work I've done, and don't hesitate to reach out if you have questions or opportunities!