LATAM Software Engineers: Coding Tasks for AI Evaluation
Core
Review and assess coding tasks and evaluation harnesses designed to test AI agents' software capabilities.
Role type
Software engineer (AI evaluation study participant)
Builds
AI evaluation frameworks and programming environments
Domain
Artificial Intelligence / Software Engineering
Deliverable
production ML models
Required skills
Software engineering, code review, evaluation harness design, programming task creation, technical architecture discussion
Preferred skills
Backend development, full-stack engineering, QA automation
Technologies
Programming languages, code review tools
Responsibilities
Review realistic programming tasks for AI evaluation, assess accuracy of evaluation harnesses, provide feedback on task complexity and realism
Seniority
Mid-level, hands-on IC
