Freelance Agent Evaluation Engineer

Freelance Agent Evaluation Engineer

Mindrift

Remote

Standort
Art des Vertrags
B2B

Hexjobs Insights

Mindrift seeks Freelance Agent Evaluation Engineers for project-based AI opportunities. Requires 3+ years software development (Python), Git, and familiarity with Docker. Remote role.

Schlüsselwörter

software development
Python
Git
JSON
YAML
Docker
LLM limitations
English proficiency
test cases
evaluation design

Mindrift connects specialists with project-based AI opportunities for leading tech companies, focused on testing, evaluating, and improving AI systems. Participation is project‑based as an independent freelance contributor and does not create an employment relationship with Toloka or our clients.What this opportunity involvesAs an independent freelance contributor, you choose which projects to join and how you organize your work, as long as deliverables meet the project requirements and deadlines.While each project involves unique tasks, contributors may:Create structured test cases that simulate complex human workflowsDefine gold-standard behavior and scoring logic to evaluate agent actionsAnalyze agent logs, failure modes, and decision pathsWork with code repositories and test frameworks to validate your scenariosIterate on prompts, instructions, and test cases to improve clarity and difficultyEnsure that scenarios are production-ready, easy to run, and reusableWhat we look forThis opportunity is a good fit for software engineers, open to part-time, non-permanent projects. Ideally, contributors will have: 3+ of software development experience with strong Python focusExperience with Git and code repositoriesComfortable with structured formats like JSON/YAML for scenario descriptionUnderstanding core LLM limitations (hallucinations, bias, context limits) and how these affect evaluation designFamiliarity with DockerEnglish proficiency - B2How it worksApply → Pass qualification(s) → Select a project → Complete tasks on your own schedule within project timelines→ Get paidProject time expectationsFor this project, tasks are estimated to require around 6–10 hours of work per week during active phases, depending on the tasks you choose to complete. This is an estimate only and does not create any minimum or guaranteed hours.PaymentPaid freelance contributions, with rates that may be equivalent to up to $80/hour* (project‑ and task‑based)Fixed project rate or individual rates, depending on the projectSome projects include incentive payments*Note: Rates vary based on expertise, skills assessment, location, project needs, and other factors. Higher rates may be offered to highly specialized experts. Lower rates may apply during onboarding or non-core project phases. Payment details are shared per project.

Anmelden, um vollständige Details zu sehen

Erstellen Sie ein kostenloses Konto, um auf die vollständige Stellenbeschreibung zuzugreifen und sich zu bewerben.

Aufrufe: 14
Veröffentlichtvor 4 Tagen
Läuft abin 26 Tagen
Art des VertragsB2B

Ähnliche Jobs, die für Sie von Interesse sein könnten

Basierend auf "Freelance Agent Evaluation Engineer"

Keine Angebote gefunden, versuchen Sie, Ihre Suchkriterien zu ändern.