Experiences

SWE Intern, Hardware Engineering

Building agentic developer tooling for hardware teams in Shanghai, running on local models.

• Built and iterated on an agentic dev tool running local models on Apple MLX-LM, tuned for factory environments so it stays smooth on machines with 8GB of RAM.
• Built an internal AI skills-sharing platform (Next.js and PostgreSQL) with corporate OAuth and LDAP access management, grown to 100+ users and 7,000+ visits per week.
• Designed and implemented context compression, long-term memory, and skills/MCP progressive disclosure for an AI hardware tool.
• Worked with hardware teams to turn lab workflows, internal CLI tools, and hardware testing details into installable AI skills.

Intern, SDET

Interned at GoFreight as a Software Development Engineer in Test.

• Developed an AI test generation and error healing system with Claude and Playwright to replace current workflows.
• Automated E2E testcase execution with Selenium, identifying anomalies in APIs, UI behaviors, and visual appearances.
• Chained different CI tools and maintained Docker containers and adapted them for different environments.

Trainee, Taiwan Marine Corps

Spent 4 months learning how to defend a democracy. We were trained on teamwork, swimming, weaponry, emergency healthcare, urban warfare, and supporting professional soldiers.

Intern, Systems Integration

In charge of a new project about brainwave (EEG) signal acquisition and processing.

• Built Python framework to stream brain signals from different hardware; developed portal with HTML & JS for realtime visualization.
• Optimized Python framework with parallel processing & threading to perform realtime filtering, separation, & analysis of signals.
• Scripted Arduino systems to stream analog sensor data into chip and then server; analyzed & modified circuits for brain measurement.
• Produced patent analyses & market reports for commercially available brain-computer interface devices and mixed reality systems.

Intern, NLP Research

Built intelligent systems with natural language understanding and common knowledge.

• Developed a prototype information extraction system to extract biochemical interactions from research papers with spaCy (for NLP).
• Parsed 100% of Chinese Wikipedia for text mining to construct common knowledge graph with Python and SQL.
• Designed an error-tolerant word-rec algorithm for Chinese pharma terms, with 97%+ correctness & 300% avg. runtime improvement.
• Assessed the use of pretrained word embeddings in meaning-disambiguation and visualized results with Python, HTML, CSS.