Portfolio

AI · Backend · Cloud · Systems

ChunYuan Hsu

AI/backend engineer working across agents, infrastructure, and applied ML.

Master of Science in Data Science student at the University of Michigan building AI agents, backend infrastructure, and applied machine learning systems across production and research environments.

Originally from Tainan, Taiwan, I took an unconventional route into software: civil engineering to computer science. Away from work, I enjoy watching sports, especially baseball, basketball, and football; going to the gym; playing darts; Linux ricing and interface customization.

About Me Download CV
Portrait of ChunYuan Hsu

01 / Experience

Production evidence, in context.

May 2026 – Aug 2026

Hsinchu, Taiwan

TSMC

Digital Workflow Development Department Intern

Building an AI-agent workflow for structured backend incident investigation across alerts, logs, and metrics.

  • Developed an AI-agent workflow with the Claude Agent SDK to automatically triage backend alerts and generate structured incident-analysis reports.
  • Built integrations to ingest alerts from Alertmanager and retrieve logs and metrics from Kubernetes workloads via ELK and Prometheus.
More detail
  • Designed a hypothesis-driven investigation loop that correlates alerts, logs, and metrics to identify likely root causes and summarize actionable findings for engineering teams.

Jan 2025 – Jul 2025

Taiwan

QNAP

Backend R&D Internship

Built retrieval and developer-tooling systems, improved a Go service, and diagnosed production reliability problems.

  • Built a retrieval-augmented Jira issue search system using AWS Bedrock and ChromaDB embeddings, increasing developer issue-resolution efficiency by 50%.
  • Refactored Device Avatar microservices from Python to Go, achieving a 30% performance gain and optimizing deployment on Kubernetes.
More detail
  • Developed an MCP-based Jira search server that integrates with IDEs, enabling developers to query and explore issues directly from their coding workflow.
  • Diagnosed and patched a critical memory leak in cloud production by correlating Grafana metrics with execution traces.
  • Migrated the Konnyaku service from Python 2 to Python 3 and deployed it on Kubernetes.
  • Added token authentication and unit tests to Device Avatar.
  • Benchmarked MongoDB and Couchbase for service storage.
  • Investigated DDNS worker failures during RabbitMQ scaling.
  • Investigated NATS connection failures under production scaling.

02 / Selected work

What I contributed, and what the project demonstrated.

Research

Lilac

Context
A broader cross-cloud Infrastructure-as-Code lifting research system that learns reusable mappings from deployed cloud state to Terraform and uses LLM assistance with symbolic and Terraform-native verification.
My contribution
  • Built a focused graph-based lifting workflow for concrete Terraform mappings, primarily on Azure, including JSON-schema and dependency cases.
  • Implemented Azure cloud-state collection and a GCP resolver that uses an LLM to infer service-specific CLI commands, then parses and caches them by asset type.
Project result
  • The work established an implementation-oriented foundation for Lilac's broader cloud-agnostic, correctness-aware lifting pipeline.
Read project report

Research

Toward Interpretable Brain Age Prediction and AD Classification

Context
A University of Michigan EECS 545 team project for brain-age regression and Alzheimer's Disease classification using structural MRI from OpenBHB and ADNI.
My contribution
  • Focused on infrastructure and data processing, including generation of patch-level 3D embeddings and coordinates used by the downstream models.
Project result
  • 0.873 diagnostic accuracy
  • 0.775 macro F1
  • 3.54-year MAE
  • 0.966 R²
Read project report

Product

VizThinker

Context
A graph-based interface for interacting with LLMs that replaces a single linear transcript with a visual conversation graph.
My contribution
  • Implemented branching and node-based history navigation for complex idea exploration using Node.js, React, and Python.
  • Deployed the application on Google Cloud Platform.
Project result
  • The project produced a graph interface for branching through conversation history.
View live project View source

03 / More work

The complete engineering archive.

Open Projects
  1. Jira Issue Search
  2. Issue Search MCP
  3. File Translator
  4. AZtec Image Comparison
  5. MIPS CPU Architecture
  6. OS Nachos
  7. Advanced Compiler
  8. Quantum Event Identification and Simulation of Quantum Event-Learning Procedures

04 / Profile

An interdisciplinary route into systems.

Master of Science in Data Science
University of Michigan · Sep 2025 – Present

Background and records · Full CV

Languages
Python · C++ · Go

AI & ML
PyTorch · AI Agents · Claude Agent SDK · LLM Integration (AWS Bedrock) · RAG (ChromaDB) · Embeddings · Semantic Search

Cloud & DevOps
Docker · Kubernetes · AWS · GCP · GitLab CI/CD · Prometheus · Elastic Stack (ELK) · Alertmanager · Grafana · NATS

Frameworks & Systems
Node.js · React · Linux (Debian, Arch) · Git · Scrum

05 / Latest writing

Notes from the work.

All posts

06 / Contact

Let's compare notes.

Email ChunYuan