Hello! 👋

I'm Yiming Feng

AI/ML Engineer & Duke MSCS Student

About Me

I'm an AI/ML Engineer and Duke MSCS student focused on deep learning, model development, and building reliable ML systems. I work primarily with PyTorch to design and train neural networks (CNNs, MLPs), and I build end-to-end, production-ready ML pipelines aimed at reliability and performance.

Alongside my ML work, I have supporting experience in full-stack development and system design, which helps me integrate models cleanly into real applications. I also bring strong engineering fundamentals in Docker, Kubernetes, Linux, and backend systems, enabling scalable and maintainable deployment of machine learning services.

My goal is to create robust, maintainable, and high-performance AI systems that work dependably in real-world environments.

Python C++ C JavaScript / TypeScript Java PyTorch Scikit-learn TensorFlow CNNs Transfer Learning Image Classification Object Detection (YOLO) OpenCV MediaPipe LLMs Prompt Engineering Deep Reinforcement Learning Multi-Agent RL Self-Play Training Docker Kubernetes CI/CD (GitHub Actions) React Nuxt Node.js FastAPI WebSocket MongoDB SQL Redis

Education

Master of Science in Computer Science

Duke University

Aug 2025 - May 2027 (Expected)
  • GPA: 4.0

Bachelor of Science in Computer Science

University of California, Davis

Jul 2022 - Jun 2025
  • GPA: 3.9
  • Honors Graduation

Experience

AI/ML Intern

Qorvo

May 2026 - Present
  • Develop AI/ML prototypes and proof-of-concept solutions for enterprise and business process applications.
  • Conduct data preprocessing, exploratory analysis, and model experimentation using Python and machine learning frameworks.
  • Collaborate with cross-functional stakeholders to evaluate AI/ML use cases and support internal technical presentations and documentation.

Graduate Teaching Assistant

Duke University CS Department

Sep 2025 - Present
  • Evaluate assignments promptly and provide detailed, actionable feedback that strengthens student understanding and performance.
  • Hold weekly office hours to answer questions and debug coding issues, improving comprehension of core course material.
  • Lead pre-exam review sessions with targeted practice problems to reinforce key concepts and improve exam readiness.

Mathematics Reader

UC Davis Math Department

Sep 2024 - Dec 2024
  • Graded coursework and delivered detailed feedback that improved students' problem-solving skills and mathematical understanding.

System Architect Intern

Guangdong Yixun Technology

Jul 2023 - Aug 2023
  • Integrated Vue.js with Spring Boot to streamline the user experience and improve system responsiveness.
  • Raised YOLOv3 image recognition accuracy by developing and curating specialized training datasets.
  • Built monitoring pipelines with Prometheus and Grafana to surface system health and performance metrics.

Projects

01

StyleDou

A style-conditioned DouDizhu RL agent built on DouZero/DouZero+, with opponent-style LSTM encoders and auxiliary next-action prediction. Achieved ~98% win rate vs. Random and ~83% vs. RLCard.

Reinforcement LearningOpponent ModelingDeep Monte Carlo
02

SafeBench-DRA

An offline Chinese–English benchmark for evaluating security failures in deep-research agents using deterministic retrieval, adversarial tool-response overlays, and trace-level scoring.

LLM AgentsDeep Research AgentBenchmarkingAgent Security
03

Hand Gestures Classifier

A multimodal deep learning system for classifying 18 hand gestures using Graph Neural Networks, ResNet-34, and late fusion. Achieved 99.72% accuracy on the HaGRID dataset.

GNNResNet-34Image ClassificationPyTorch
04

LOL-Win-Prediction

Predicted win probability in League of Legends matches using a deep neural network trained on first 15 minutes of in-game data. Improved local robustness with PGD attacks and TRADES.

Adversarial RobustnessPGDTRADESDeep Learning
05

Proactive-AI

A Chrome extension that detects user hovers and selections to surface relevant AI tools in place — enabling real-time code explanation, summarization, equation graphing, table extraction, and OCR.

Chrome ExtensionAI ToolsOCR
06

Chinese Handwritten Digit Classifier

Deep learning models with VGG16 and LeNet to classify handwritten Chinese numerals. Achieved ~97% accuracy on the Chinese MNIST dataset.

CNNVGG16LeNet
07

Blood-On-Mahjong

A real-time multiplayer Sichuan Mahjong web application with WebSocket-based gameplay and Google OAuth authentication, designed for scalable Kubernetes-based hosting.

TypeScriptWebSocketGoogle OAuthKubernetesCI/CD
08

WOAA-trading

A full-stack stock trading simulation platform with real-time market data streaming and historical backtesting, letting users practice and refine trading strategies without financial risk.

Full-StackWebSocketBacktesting