AI Agent Evaluation Engineer - Project-Based

Mindrift; Argentina; Presencial; ARS 49.308.150 - 70.226.760; Jornada completa

Descripción de la vacante

Mindrift in Argentina seeks software developers to create and evaluate challenging tasks for AI coding agents. You will design realistic developer environments and iterate tasks based on agent performances.

Applicants should have over 5 years of experience with a core stack including Python, JavaScript, and Docker, and demonstrate strong English proficiency (B2+). Compensation is up to $30/hr based on performance, with tasks estimated to take around 20 hours each.

Formación

• 5+ years of experience in software development.
• Proficiency in Python (FastAPI) and JavaScript/TypeScript (React).
• Experience with Docker, Postgres, Kafka, and Redis.

Responsabilidades

• Create realistic developer tasks and evaluate AI agent performance.
• Design tasks and write tests to verify solutions.
• Iterate on tasks based on feedback and refine for fairness.

Conocimientos

Software development experience

Python (FastAPI)

JavaScript/TypeScript (React)

Docker

Postgres

Kafka

Redis

Test writing (functional, integration)

English proficiency (B2+)

Descripción del empleo

Mindrift in Argentina seeks software developers to create and evaluate challenging tasks for AI coding agents. You will design realistic developer environments and iterate tasks based on agent performances.

Applicants should have over 5 years of experience with a core stack including Python, JavaScript, and Docker, and demonstrate strong English proficiency (B2+). Compensation is up to $30/hr based on performance, with tasks estimated to take around 20 hours each.