Logo
Mindrift

Evaluation Scenario Writer - AI Agent Testing Specialist

Mindrift, New York, New York, us, 10261

Save Job

About Mindrift At Mindrift, innovation meets opportunity. We use the power of collective human intelligence to ethically shape the future of AI.

What We Do Mindrift’s platform, launched and powered by Toloka, connects domain experts with cutting‑edge AI projects from innovative tech clients. Our mission is to unlock the potential of GenAI by tapping into real‑world expertise from across the globe.

About The Role We’re looking for someone who can design realistic and structured evaluation scenarios for LLM‑based agents. You’ll create test cases that simulate human‑performed tasks and define gold‑standard behavior to compare agent actions against. You’ll work to ensure each scenario is clearly defined, well‑scored, and easy to execute and reuse. You’ll need a sharp analytical mindset, attention to detail, and an interest in how AI agents make decisions.

Responsibilities

Design structured test scenarios based on real‑world tasks

Define the golden path and acceptable agent behavior

Annotate task steps, expected outputs, and edge cases

Work with devs to test your scenarios and improve clarity

Review agent outputs and adapt tests accordingly

How To Get Started Simply apply to this post, qualify, and get the chance to contribute to projects aligned with your skills on your own schedule. From creating training prompts to refining model responses, you’ll help shape the future of AI while ensuring technology benefits everyone.

Requirements

Bachelor’s and/or Master’s Degree in Computer Science, Software Engineering, Data Science/Data Analytics, Artificial Intelligence/ML, Computational Linguistics/NLP, Information Systems or related fields

Background in QA, software testing, data analysis, or NLP annotation

Good understanding of test design principles (reproducibility, coverage, edge cases)

Strong written communication skills in English

Comfortable with structured formats like JSON/YAML for scenario description

Can define expected agent behaviors (gold paths) and scoring logic

Basic experience with Python and JS

Curious and open to working with AI‑generated content, agent logs, and prompt‑based behavior

Ready to learn new methods, able to switch between tasks and topics quickly in challenging, complex guidelines

Our freelance role is fully remote so you just need a laptop, internet connection, time available and enthusiasm to take on a challenge

Nice to Have

Experience in writing manual or automated test cases

Familiarity with LLM capabilities and typical failure modes

Understanding of scoring metrics (precision, recall, coverage, reward functions)

Benefits

Get paid for your expertise, rates can go up to $60/hour depending on skills, experience, and project needs

Flexible, remote, freelance project that fits around professional or academic commitments

Advanced AI project experience to enhance portfolio

Influence how future AI models understand and communicate in your field of expertise

#J-18808-Ljbffr