Hello! 👋

I'm Yiming Feng

AI/ML Engineer & Duke MSCS Student

About Me

I'm an AI/ML Engineer and Duke MSCS student specializing in LLMs, Agentic AI, and machine learning systems. I build end-to-end AI solutions, including RAG pipelines, multi-agent workflows, and deep learning models, with a focus on scalable, reliable, and production-ready applications.

Python C++ Java JavaScript / TypeScript SQL PyTorch Scikit-learn TensorFlow Deep Learning Computer Vision Reinforcement Learning Model Evaluation LLMs Agentic AI RAG OpenAI SDK Prompt Engineering Vector Search Hybrid Retrieval Embedding Models LLM Evaluation Agent Security Databricks Docker Kubernetes CI/CD GitHub Actions Linux Git FastAPI REST APIs WebSocket MongoDB Redis PostgreSQL React Nuxt Node.js

Education

Master of Science in Computer Science

Duke University

Aug 2025 - Dec 2026 (Expected)
  • GPA: 4.0
  • AI/ML Concentration

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
  • Designed and developed a multi-stage deterministic agentic GenAI workflow (As-Is Documentation Agent) using OpenAI SDK and Databricks to analyze SAP source code and technical artifacts and automatically generate solution design and process documentation, processing 50+ files per run with 95% file coverage and producing complete documentation in under 5 minutes for less than $3 per run.
  • Developed RICEFW Agent, an enterprise RAG chatbot integrating 5+ internal knowledge sources and 5K+ documents, achieving 92% Recall@5 and 95% groundedness on 200+ representative queries through hybrid semantic and keyword retrieval.
  • Built CI/CD and continuous monitoring pipelines for both AI systems, enabling automated deployment, performance tracking, and reliable iteration while leveraging AI to accelerate post-merger knowledge integration and standardization across enterprise systems and processes.

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.

System Architect Intern

Guangdong Yixun Technology

Jul 2023 - Aug 2023
  • Integrated Vue.js and Spring Boot to improve application usability and responsiveness; improved YOLOv3 recognition accuracy through specialized dataset development.
  • Built system-health and performance monitoring pipelines using Prometheus and Grafana.

Projects

01

As-Is Documentation Agent

A multi-stage deterministic agentic GenAI workflow (As-Is Documentation Agent) using OpenAI SDK and Databricks to analyze SAP source code and technical artifacts and automatically generate solution design and process documentation, processing 50+ files per run with 95% file coverage and producing complete documentation in under 5 minutes for less than $3 per run.

Agentic AILLMsDatabricksOpenAI SDKLangGraph
02

RICEFW Agent

An enterprise RAG chatbot integrating 5+ internal knowledge sources and 5K+ documents, achieving 92% Recall@5 and 95% groundedness on 200+ representative queries through hybrid semantic and keyword retrieval.

RAGLLMsVector SearchDatabricks
03

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
04

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
05

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
06

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
07

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
08

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
09

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
010

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