Park Kharuehadech

Quality Assurance Automation Engineer with extensive experience designing, developing, and maintaining scalable automated test solutions in SAFe Agile environments. Proven ability to improve software quality, streamline testing processes, and support CI/CD pipelines. Maintains regular communication with DevOps teams to monitor builds, deployments, and environment health across the software development lifecycle.

Also practicing as an AI/LLM Evaluation Engineer with hands-on experience building prompt evaluation pipelines and agentic workflow test suites using Promptfoo and Arato.ai. Applies red-teaming and adversarial testing methods to surface failure modes, bias patterns, and safety gaps. Designs evaluation frameworks to measure LLM output quality across accuracy, consistency, task completion, and hallucination rates. Bridges traditional QA discipline with AI evaluation rigor to build testable, trustworthy AI systems.