Skip to content
View RennaWu's full-sized avatar

Achievements

Achievement: Pair ExtraordinaireAchievement: Pull Sharkx2Achievement: YOLO

Achievements

Achievement: Pair ExtraordinaireAchievement: Pull Sharkx2Achievement: YOLO

Highlights

  • Pro

Block or report RennaWu

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 is supported. This note will only be visible to you.
Report abuse

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

Report abuse
RennaWu/README.md

Hi, I'm Renna 👋

Data & AI Engineering | MSIS @ Northeastern University

📍 Based in Toronto, Canada · 🎓 Graduating Dec 2026 · 💼 Open to Fall 2026 Co-op & Full-Time roles

🔭 About Me

I'm a Master's student in Information Systems at Northeastern University with 6+ years of business experience transitioning into data and AI engineering. I love building systems that turn messy data into clear decisions — from normalized databases to multi-agent AI pipelines.

  • 🛠️ Currently working on: AI Applications (INFO 7375) and Data Architecture for BI (DAMG 7370)
  • 🌱 Learning: distributed systems, agentic AI patterns, LLM fine-tuning on Apple Silicon
  • 👩‍🏫 Teaching Assistant for INFO 5100 (Java Application Engineering) — 2 semesters
  • 🌐 Languages: Mandarin (native) · Japanese (fluent, MBA in Tokyo) · English

🚀 Featured Projects

Project Stack Highlights
Portfolio Risk Radar Python · Claude API · rapidfuzz · Slack Screens entities against 5,800+ UN/UK/World Bank/OFAC sanctions · LLM-as-filter removes 60–80% of false positives
Text-to-SQL LoRA + MLX Qwen 2.5-3B · LoRA · Apple MLX Fine-tuned 3B LLM in ~33 min on MacBook M4 · +4% Exact Match, +12.3% BLEU on held-out test set
Kafka Multi-Agent Fraud Detection Apache Kafka 3.6 · Docker · Python 3-agent event-driven workflow · idempotent processing · KRaft mode · production-style durability
TechFlow RDBMS Oracle 19c · React · Node.js · Express 15-entity 3NF database · 20+ REST endpoints · Led team of 3

💼 Tech Stack

Languages: Python · Java · SQL · JavaScript · Swift
Data & ML: pandas · NumPy · scikit-learn · PyTorch · Hugging Face · rapidfuzz
Databases: Oracle 19c (3NF) · MongoDB · MS SQL Server
Backend & Infra: Node.js · Express · Apache Kafka (KRaft) · Docker · REST APIs
Frontend: React · SwiftUI
AI / LLM: Claude API (Anthropic) · MLX · LoRA · MCP · Prompt Engineering · Multi-Agent Patterns

📜 Certifications (2026)

  • Anthropic: Claude Certified Architect (Foundations) · Building with Claude API · Claude Code in Action · Intro to MCP · Intro to Agent Skills

📫 Connect

Pinned Loading

  1. agentic-ai-pubsub-kafka agentic-ai-pubsub-kafka Public

    Production-style multi-agent fraud detection with Apache Kafka 3.6 (KRaft mode). Bidirectional event loop, idempotency keying, 5-layer evidence chain.

    Python 1

  2. text-to-sql-lora-mlx text-to-sql-lora-mlx Public

    Fine-tuning Qwen 2.5-3B for Text-to-SQL using LoRA + Apple MLX on consumer hardware. +12.3% BLEU, +4% Exact Match in ~33 min on M4.

    Jupyter Notebook

  3. portfolio-risk-radar portfolio-risk-radar Public

    LLM-augmented risk monitoring pipeline. Screens entities against multi-jurisdictional sanctions lists (UN/UK/World Bank/OFAC) + adverse media. Uses Claude for entity disambiguation. Routes alerts t…

    Python 1

  4. wine-quality-prediction wine-quality-prediction Public

    Predicting wine scores from structured metadata using KNN and Random Forest — 130K-record study with business case translation

    Jupyter Notebook 1

  5. techflow-rdbms techflow-rdbms Public

    Full-stack internship recruitment system: Oracle 3NF database (15 entities) + React/Node.js + 20+ REST APIs. Designed ERD, RBAC framework, and built complete frontend. Course project, DAMG 6210 @ N…

    1

  6. product-recommendation-feed product-recommendation-feed Public

    Swift