Mindrift

Freelance Agent Evaluation Engineer

Mindrift
Apply
11 hours ago
Remote, PhilippinesSenior

Responsibilities

  • Build realistic simulated developer environments with codebases, infrastructure, tickets, documentation, and conversations.
  • Design challenging coding-agent tasks, prompts, and solvability criteria from intermediate environment states.
  • Write functional and integration tests that verify agent solutions and accommodate all valid approaches.
  • Review agent solutions, analyze failures, and refine tasks and tests based on QA feedback.
  • Ensure evaluations are fair, robust, neither overly strict nor overly lenient.

Requirements

  • 5+ years of software development experience.
  • At least 3 years of professional experience in related roles or domains for QA automation/testing or cybersecurity candidates.
  • Experience with Python and FastAPI, JavaScript/TypeScript and React, Docker, Postgres, Kafka, and Redis.
  • Experience writing functional and integration tests.
  • Master’s degree in a listed or related field, or a Bachelor’s degree with five years of relevant experience.
  • English proficiency at B2 level or higher.
  • Applicants must submit a CV in English and indicate their English proficiency.

Benefits

  • Remote, part-time freelance project-based work.
  • Flexible work that can fit around primary professional or academic commitments.
  • Opportunity to work on advanced AI projects and enhance a professional portfolio.
  • Opportunity to influence how future AI models understand and communicate in the field.
  • Paid per accepted task, with compensation up to the equivalent of $30/hr depending on qualification tier and efficiency.
  • Participation is project-based and not permanent employment.
Mindrift

About Mindrift

1,001-5,000 employees

Mindrift builds an expert-sourcing platform that connects domain specialists to project-based work training and evaluating generative AI models, including supervised fine-tuning, RLHF, evaluation, and red-teaming. It is built and operated by Toloka, part of Nebius Group, and run from Amsterdam, Netherlands. Work is fully remote and freelance, serving global technology companies developing and improving large AI systems.

Contact me