Curriculum Vitae

Professional Profile

Final‑year Ph.D. candidate in Machine Learning & Data Science (University of Queensland, expected 2025) who thrives at the intersection of research and production. I design trustworthy, interpretable time‑series models and turn them into robust, cloud‑native services. Highlights include a 90 % boost in metadata‑extraction efficiency for engineering drawings and end‑to‑end MLOps pipelines on hardened AWS infrastructure. I value clean code, reproducible science, and security‑first engineering.

Core Strengths

• Time‑Series & Sequential Modelling – Transformers, GNNs, Multiple‑Instance Learning, noisy‑label learning, advanced attention mechanisms
• Full‑Stack Development – Laravel 12 (TALL stack), Livewire, Alpine JS, Tailwind CSS, REST & GraphQL APIs
• Cloud & DevOps – AWS (S3, IAM, Glue, Athena, Lambda, CloudWatch), Terraform, Docker, Ubuntu server hardening, Cloudflare DNS/SSL
• MLOps & Automation – PyTorch, TensorFlow, scikit‑learn, MLflow, GitHub Actions, Bash/Python CI/CD scripting
• Data Engineering – Apache Spark, AWS Glue ETL, Pandas / Polars, Athena/Presto, SQL optimisation
• Security & Compliance – Least‑privilege IAM, MFA enforcement, key‑rotation, secure‑SDLC practices

Technical Toolkit

• Languages Python, TypeScript / JavaScript, PHP, Bash, SQL
• ML / DL PyTorch, TensorFlow 2, scikit-learn, PyG, DGL, Hugging Face, Optuna
• Web Laravel (Jetstream & Filament), Node.js, Express, React, Tailwind CSS, Livewire, Blade
• Data Pandas, Polars, NumPy, Spark (PySpark), AWS Glue, Apache Parquet, Arrow
• Cloud AWS S3, EC2, RDS, Lambda, Glue, Athena, IAM, CloudWatch, Route 53
• DevOps Docker, Docker Compose, Git, GitHub Actions, Terraform, Ansible
• Databases MySQL, PostgreSQL, DynamoDB, SQLite
• Visualization Matplotlib, Plotly, Superset, Metabase
• OS / Platforms Ubuntu, macOS, Windows
• Testing & QA PyTest, PHPUnit, Jest, Cypress
• Other LaTeX, Markdown, Jupyter, VS Code, PyCharm

Education

• Ph.D. Machine Learning & Data Science, The University of Queensland — 2022 – 2025 (expected)
• M.S. Computer Science, The University of Queensland — 2020 – 2021
• B.Eng. Communication Engineering, Beijing University of Posts & Telecommunications — 2014 – 2018

Work Experience

• Full‑Stack Web Developer — Actech International
  Architect & Lead Developer of Panelo.ai
  • Designed and launched a secure multi‑tenant SaaS platform to streamline lifting‑design workflows.
  • Achieved 90 % faster metadata extraction via OpenAI‑powered vision and NLP models.
  • Built with the TALL stack and Filament Admin; integrated AWS S3 with event monitoring and CloudTrail for auditability.
  • Implemented automated PDF stamping, task management, and email notification services.

• Junior DevOps & Cloud Automation Engineer — Freelance / Contract
  • Authored Python asset‑verification scripts, eliminating manual image checks and generating reproducible reports.
  • Administered AWS IAM, CloudWatch, and key‑rotation policies; managed DNS and SSL/TLS via Cloudflare.
  • Hardened Ubuntu servers on Vultr and deployed Metabase & Superset, automating data‑insight reporting pipelines.

• Teaching Assistant — The University of Queensland
  Supported courses in Web Information Systems, Data Structures & Algorithms, and Machine Learning; delivered tutorials and assessment feedback.

• Research Assistant — The University of Queensland
  Deployed DetectionLab for cybersecurity simulations; analysed attack data with Elasticsearch & Kibana.

Recent Highlights

• Panelo.ai  – AI‑driven panel‑drawing management platform (https://panelo.ai/)
  Streamlines lifting‑design workflows, automates metadata extraction and report generation, and ensures compliance through intelligent drawing management.

Publications

Adapting to the Stream: An Instance-Attention GNN Method for Irregular Multivariate Time Series Data

**Kun Han**, Abigail M.Y. Koay, Ryan K.L. Ko, Weitong Chen & Miao Xu (2025). “Adapting to the Stream: An Instance-Attention GNN Method for Irregular Multivariate Time Series Data.” *Frontiers of Computer Science*, 19(8):198340. https://doi.org/10.1007/s11704-024-40449-z

HITS: Hierarchical Interpretable Time Series Classification via Multiple Instance Learning

Kun Han, Abigail M.​Y. Koay, Ryan K.​L. Ko, Weitong Chen & Miao Xu (2025). “HITS: Hierarchical Interpretable Time Series Classification via Multiple Instance Learning.” *Proceedings of the International Joint Conference on Neural Networks (IJCNN 2025)*. Rome, Italy.

Mining Irregular Time Series Data with Noisy Labels: A Risk Estimation Approach

Kun Han, Abigail M.Y. Koay, Ryan K.L. Ko, Weitong Chen & Miao Xu (2025). “Mining Irregular Time Series Data with Noisy Labels: A Risk Estimation Approach.” *Proceedings of the Australasian Database Conference (ADC 2025)*, pp. 293–307. Springer, Singapore.

Investigating Active Positive-Unlabeled Learning with Deep Networks

Kun Han, Weitong Chen, & Miao Xu. (2022). “Investigating Active Positive-Unlabeled Learning with Deep Networks.” *Proceedings of the 34ᵗʰ Australasian Joint Conference on Artificial Intelligence (AI 2021)*, pp. 607–618. https://doi.org/10.1007/978-3-030-97546-3_49

Service & Leadership

• Contributor to open‑source projects and academic peer review
• Active member in interdisciplinary research groups and tech communities
• Currently a member of 43 Slack workspaces, facilitating collaboration across teams