AI Evaluation • Localization QA (LQA) • Documentation Engineering • Human–AI Workflow Design

I have over 15 years of experience in Localization QA (LQA), manual QA, LiveOps, and content operations for the gaming industry.

My current focus is AI evaluation, documentation engineering, workflow design, and structured Human–AI collaboration. I evaluate LLM outputs using structured review methodologies while building reusable documentation systems and workflows that improve quality, consistency, and traceability.

• AI Evaluation
• LLM Evaluation
• Localization QA (LQA)
• Documentation Engineering
• Human–AI Workflow Design
• Human–AI Collaboration

Open-source framework for structured Human–AI collaboration through documentation architecture, workflow design, and knowledge organization.

🔗 https://github.com/stevan-michael/user-package-public

AI-assisted Localization QA workflow designed to improve translation consistency, review quality, and repetitive QA processes.

• LLM Evaluation
• RLHF-style Evaluation
• Preference Ranking
• Pairwise Comparison
• Rubric-based Assessment
• Multi-turn Conversation Analysis
• Reasoning Verification
• Evidence-based Review

• Localization QA (LQA)
• English ⇄ Indonesian Localization
• Linguistic QA
• Manual QA Testing

• Documentation Engineering
• Workflow Design
• Knowledge Organization
• Technical Documentation
• Markdown Documentation

• LinkedIn: https://www.linkedin.com/in/michaelpitoy/
• GitHub: https://github.com/stevan-michael