Skip to content
View SunnyJaneH's full-sized avatar

Block or report SunnyJaneH

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
SunnyJaneH/README.md

Hi there, I'm Jie (Jane) Heng 👋

MS in Applied Data Intelligence @ San Jose State University | Imperial College London Alumna

Bridging the gap between Software Project Management and Technical Execution. I build scalable data pipelines, deep learning models, and full-stack AI applications.

🛠 Technical Toolbox

  • Languages: Python, Java, C++, SQL, JavaScript (Node.js/React)
  • AI & Deep Learning: PyTorch, TensorFlow, CNNs (AlexNet), NLP, Scikit-learn
  • Data Engineering: Spark, Hadoop, HDFS, Airflow, dbt, Snowflake, MongoDB
  • Agentic AI: LangGraph, Claude MCP (Model Context Protocol), FastAPI
  • Full Stack: React, Express, RESTful APIs, Docker

🚀 Featured Projects

🤖 [Stateful Agentic AI Framework (LangGraph)]

  • Refactored sequential scripts into a Stateful Graph Architecture with modular nodes (Planner, Reviewer, Supervisor).
  • Implemented fault-tolerant execution and shared memory for complex agentic workflows.
  • Tech: Python, LangGraph, OpenAI/Claude API

👁️ [Deep Learning: AlexNet from Scratch]

  • Built and trained the AlexNet architecture using PyTorch on ImageNet subsets.
  • Optimized performance via custom Kaiming initialization and Cosine Annealing LR scheduling.
  • Tech: PyTorch, Computer Vision, GPU Computing

⛓️ [Distributed Spatial Join for TB-Scale Data]

  • Designed a scalable MapReduce pipeline at Imperial College London to process neuroscience data.
  • Integrated SEEP big data platform with HDFS to enhance throughput.
  • Tech: C++, Hadoop, Distributed Systems

🍽️ [MCP Recipe Server & Full-Stack Integration]

  • Built a local MCP server to expose external APIs (TheMealDB) to LLMs via JSON endpoints.
  • Tech: Python, Node.js, React, MCP Inspector

📫 Connect with me:

Popular repositories Loading

  1. data226 data226 Public

    Python

  2. build_mau build_mau Public

    My dbt project for Snowflake

  3. pinecone-recommendation pinecone-recommendation Public

    This is an airflow job which use pinecone to search the top 5 similar recommended articles.

    Python

  4. lab2_stockAnalysis_dbt lab2_stockAnalysis_dbt Public

  5. lab2-StockAnalysis-dbt lab2-StockAnalysis-dbt Public

    This project implements a full data analytics pipeline using Snowflake, Airflow, dbt, and Superset to analyze stock data for NVIDIA (NVDA).

    Python

  6. tensorrec tensorrec Public

    Forked from jfkirk/tensorrec

    A TensorFlow recommendation algorithm and framework in Python.

    Python