Frank Vu

I combine AI engineering, software architecture, and software quality to build and validate reliable software systems. My focus is on LLM applications that can be tested, evaluated, and trusted in production.

• AI engineering — LLM applications, RAG, AI agents
• AI quality — evaluation, testing, reliability
• Test automation — scalable test systems, CI/CD
• Software design — architecture, clean code, system design

• Relynx Requirement Intelligence

  AI · Atlassian Forge · TypeScript

  AI-powered requirement analysis for Jira, helping teams improve requirement quality and derive structured engineering insights.

• LLM Evaluation Lab

  Python · LLM · Evaluation

  A practical project for evaluating LLM outputs using reproducible tests, evaluation metrics, and representative examples.

Languages

TypeScript, Python

AI

LLM applications, Retrieval-augmented generation, AI agents, LLM evaluation

Quality

Test automation, CI/CD, Test strategy

Platforms

Atlassian Forge