CV

Education

• Ph.D. in Engineering, University of Regina, Jan 2021 - Apr 2026
  • Research: Machine learning algorithms for signal-based indoor localization
  • Awards: Saskatchewan Innovation and Excellence Graduate Scholarship (2022, 2025)
• B.Sc. in Electrical Engineering, South China Agricultural University, Sept 2013 - Jun 2017
  • Award: Second Prize Scholarship

Work experience

• Machine Learning Engineer (Contract), Mercor, Nov 2025 - May 2026
  • Designed and implemented scalable Python-based pipelines for LLM-driven task execution, improving reproducibility and system efficiency across automated workflows.
  • Built evaluation frameworks for agent-based ML systems, enabling systematic performance benchmarking and failure analysis across diverse tasks.
  • Identified and resolved failure modes in LLM-generated workflows, improving task success rates and overall system reliability.
  • Collaborated cross-functionally to refine task design and improve robustness of ML pipelines in production-like environments.
• Machine Learning Engineer Intern, Ericsson, Mar 2021 - Apr 2023
  • Designed and implemented a scalable similarity-based filtering and matching pipeline for high-dimensional signal data, improving accuracy by 55% while reducing candidate search space and computational cost.
  • Built data preprocessing and feature engineering pipelines for large-scale WiFi datasets using Python, NumPy, and Pandas.
  • Developed and benchmarked machine learning and deep learning models using PyTorch and TensorFlow.
  • Optimized model robustness by analyzing noise patterns and missing data.
  • Built evaluation and visualization tools for model analysis, performance tracking, and technical reporting.
• Sales Operations Analyst, China Telecom, Jul 2017 - Jan 2021
  • Designed SQL-based dashboards to monitor KPIs and identify sales trends.
  • Maintained customer data accuracy and generated reports for strategic decisions.
  • Collaborated with regional teams to enhance operational efficiency.

Skills

• Programming: Python, SQL, MATLAB
• ML Frameworks: PyTorch, TensorFlow, scikit-learn
• Core Skills: Machine Learning, Deep Learning, Data Pipelines, Feature Engineering, Model Training and Evaluation, Optimization, Time-Series Modeling, Signal Processing, LLM-based Workflows

Additional Information

• Location: Foster City, CA
• Work Authorization: U.S. Permanent Resident, no sponsorship required.

Publications

Exploring sampling parameters and localization performance in a multi-layer, multi-structure 5G environment

Lin, H., Li, S., Peng, W., & Purmehdi, H. Under review.

A prior-probability-driven structured attention network for indoor localization

Lin, H., Li, S., & Peng, W. Under review.

A dual-mode framework for indoor localization via temporal learning and knowledge distillation

Lin, H., Chen, Y., Li, S., & Peng, W. (2026). Ad Hoc Networks.

An enhanced group matching method with transformed fingerprints, similarity filtering, and adaptive selection for indoor localization

Lin, H., Li, S., Peng, W., & Peng, A. (2026). Internet of Things.

Group matching method for search-space reduction, development, proof, and comparison

Lin, H., Li, S., & Peng, W. (2025). Expert Systems with Applications.

A Novel SFDN+ DNN Approach for Efficient Hand Movement Recognition Using Surface Electromyography Signals

Khorram, A., Lin, H., & Peng, W. (2024). Engineering Proceedings.

A Self-Organizing Map Artificial Neural Network to Improve the K-Means Algorithm on the Classification of Different Cancers

Nakhaeepishkesh, M., Peng, W., & Lin, H. (2024). Engineering Proceedings.

Two-stage clustering for improved indoor positioning accuracy

Lin, H., Purmehdi, H., Fei, X., Zhao, Y., Isac, A., Louafi, H., & Peng, W. (2023). Automation in Construction.

Simulation of NR-V2X in a 5G Environment using OMNeT++

Pusapati, S., Selim, B., Nie, Y., Lin, H., & Peng, W. (2022). IEEE Future Networks World Forum.

Building 5G Fingerprint Datasets for Accurate Indoor Positioning

Lin, H., Purmehdi, H., Zhao, Y., & Peng, W. (2022). IEEE Future Networks World Forum.