CV

Education

======

• Ph.D. in Operations Research and Scientific Computing
  University of Michigan
  • GPA: 4.0/4.0
  • Focus: Mixed-integer & stochastic optimization, reinforcement learning
  • Advisor: Prof. Siqian Shen
• B.S. in Computational and Applied Mathematics
  University of Science and Technology of China (USTC), School for the Gifted Young

Work Experience

======

• Applied Scientist II
  Amazon.com - Scalable Optimization System for Real-Time Labor Planning
  • Develop and maintain a Java-based mixed-integer optimization model with a custom enumeration + optimization heuristic for real-time staffing in Amazon fulfillment centers, improving plan acceptance by 15% and generating $38M in annual savings.
  • System was adopted as a production-executed service and expanded across business teams, contributing an additional $40M in yearly savings.
  • Enhance the algorithm with ML classification, improving simulated performance by 4.9% within the same runtime; prototype is pending production integration.
• Applied Scientist II (Side Project) - LLM-Based Explanation for Optimization Models
  Amazon.com
  Jul 2025 – Present
  • Design a general-purpose LLM agent to interpret and explain results from optimization models by parsing given model files (e.g., MIP, LP).
  • Prototype in development; targeting generalizability across problem types and integration with production systems.
• Research Scientist Intern - Machine Learning Based Ergonomics Stowing Assistance
  Amazon.com
  May 2023 – Aug 2023
  • Built an end-to-end pipeline on AWS using SageMaker, developing a decision tree-based prediction model for product dwell time estimation.
  • Designed and integrated an ergonomics-aware stowing recommendation algorithm based on the predictions, reducing dwell time by 80% with sub-0.2s execution latency.
• Research Scientist Intern - Decomposition Algorithm for Large-scale Resource Planning Problems
  Amazon.com
  May 2022 – Aug 2022
  • Developed a dual-decomposition algorithm in Java for large-scale resource planning in transportation networks, achieving up to 17× speed-up over baseline solvers.
  • Improved total planning cost by up to 3% through better convergence and model scalability.

Technical Focus

======

• Optimization: Integer optimization, stochastic optimization, large-scale optimization
• Machine Learning: ML-integrated optimization, GenAI agents, reinforcement learning (ongoing research)

Technical Skills

======

• Programming Languages: Python, Java, C++, SQL, Matlab, R
• Solvers & Tools: Xpress, Gurobi, AWS (S3, SageMaker, Lambda)

Publications

======

Binary Quantum Control Optimization with Uncertain Hamiltonians

Xinyu Fei, Lucas T. Brady, Jeffrey Larson, Sven Leyffer, Siqian Shen. (2025). "Binary Quantum Control Optimization with Uncertain Hamiltonians," INFORMS Journal on Computing, 37(1):86-106.

Switching Time Optimization for Binary Quantum Optimal Control

Xinyu Fei, Lucas T. Brady, Jeffrey Larson, Sven Leyffer, Siqian Shen. (2025). "Switching Time Optimization for Binary Quantum Optimal Control," ACM Transactions on Quantum Computing, volume 6, issue 1, pages 1-38.

Traffic Signal Control under Stochastic Traffic Demand and Vehicle Turning via Decentralized Decomposition Approaches

Xinyu Fei, Xingmin Wang, Xian Yu, Yiheng Feng, Henry Liu, Siqian Shen, Yafeng Yin. (2023). "Traffic Signal Control under Stochastic Traffic Demand and Vehicle Turning via Decentralized Decomposition Approaches," European Journal of Operational Research, 310(2):712-736.

Binary Control Pulse Optimization for Quantum Systems

Xinyu Fei, Lucas T. Brady, Jeffrey Larson, Sven Leyffer, Siqian Shen. (2023). "Binary Control Pulse Optimization for Quantum Systems," Quantum, vol. 7, page 892.

An Optimization-and-Simulation Framework for Redesigning University Campus Bus System with Social Distancing

Gongyu Chen, Xinyu Fei, Huiwen Jia, Xian Yu, Siqian Shen. (2023). "An Optimization-and-Simulation Framework for Redesigning University Campus Bus System with Social Distancing," INFORMS Journal on Applied Analytics, 52(6):539-552.

huge: High-dimensional Undirected Graph Estimation

Haoming Jiang, Xinyu Fei, Han Liu, Kathryn Roeder, John Lafferty, Larry Wasserman, Xingguo Li, Tuo Zhao. (2019). "huge: High-dimensional Undirected Graph Estimation," R package version, 1(2).