Key Skills

Freelancer Overview

I am an experienced AI Safety Evaluation Specialist with a strong background in data labeling, annotation, and prompt evaluation for large language models (LLMs). My work involves designing safety-aligned prompts, reviewing and scoring AI outputs for compliance, and meticulously identifying unsafe content, hallucinations, and policy violations. I have hands-on experience applying complex safety policies, documenting edge cases, and providing detailed feedback to engineering teams to improve model alignment and risk mitigation. Skilled in using tools like Jira, Confluence, Excel, and simulated RL environments, I consistently deliver high-quality, structured evaluation tasks that reinforce responsible AI behavior. My technical foundation in systems engineering, combined with strong analytical and communication skills, enables me to contribute effectively to projects focused on AI safety, compliance, and quality assurance.

Labeling Experience

Education

Work History