Parcourir les catégories
Explorer
Fiverr Pro
Français
$
USD

Data Analyst
Compétences

Voir mes services


AI Evaluation & Software Engineer Intern
AirDawg Labs • Freelance
Jul 2026 - Present • 3 mos
• Developed terminal benchmark tasks to evaluate LLM reasoning, code execution, and multi-step tool use capabilities. • Built automated Python evaluation pipelines to validate model performance, scoring accuracy, and benchmark reliability. • Created CLI tools and Docker workflows for reproducible AI agent evaluation across heterogeneous runtime environments. • Improved benchmark quality via task design, unit testing, and quantitative failure pattern analysis across test suites.