Job Description
What this opportunity involves
- Review and refine realistic coding tasks based on provided production codebases with realistic scope, requirements and information sources
- Write comprehensive functional tests that validate actual end-to-end behavior and edge-cases, not just superficial checks
- Craft “fair but hard” challenges where the AI has all the context it needs, but has to work for it (information scattered across files and external sources, complex reasoning required)
- Analyze AI failures to understand what the model struggles with vs. what it masters
- Iterate based on feedback from expert QA reviewers who score your work on 7 quality criteria
What we look for
- Degree in Computer Science, Software Engineering or related fields
- 5+ years in software development, primarily Python (pytest, async/await, subprocess, file operations)
- Background in Full-Stack development, with an equal focus on building React-based interfaces and robust Back-end systems
- Experience writing tests (functional, integration – not just running them)
- Docker containers (running evaluations locally in containers)
- CI/CD understanding (GitHub Actions as a user: triggers, labels, reading results)
- English proficiency - B2
How it works
- Apply → Pass qualification(s) → Join a project → Complete tasks → Get paid
Effort estimate
Tasks for this project are estimated to take 20 hours to complete, depending on complexity. This is an estimate and not a schedule requirement; you choose when and how to work. Tasks must be submitted by the deadline and meet the listed acceptance criteria to be accepted.
Payment
- Paid contributions, with rates up to $40/hour*
- Fixed project rate or individual rates, depending on the project
- Some 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.
Get notified of similar jobs
We'll send you an email when jobs similar to "Evaluation Scenario Writer - AI Agent Testing Specialist" are posted.
Related Jobs You Might Like
View all jobs →
Research Physicist with Python Experience - Freelance AI Trainer
Mindrift
What this opportunity involves Design original computational physics problems that simulate real physics research workflows. Create problems requiring Python programming to solve (using Numpy, SciPy, Sympy). Ensure problems are computationally intensive and cannot be solved manually within reasonable timeframes (days/weeks). Develop problems requiring non-trivial reasoning chains in mechanics, electromagnetism, thermodynamics, and quantum mechanics. Base problems on real research challenges or practical applications from physics practice. Verify solutions using Python with standard physics simulation libraries. Document problem statements clearly and provide verified correct answers. What we look for Degree in Physics (Theoretical, Experimental, or Computational) or related fields. Python proficiency for numerical validation. MATLAB, R, C, SQL, Numpy, Pandas, SciPy, domain-specific libraries, Stata or knowledge of any programming language can be equivalent. 2+ years of professional experience: applied, research, or teaching experience is applicable. Experience with numerical simulation methods. Ability to design problems that mirror real physics research workflows. Creative thinking in problem design across diverse physics areas. Familiarity with physics modeling and approximation techniques. Strong written English (C1+). How it works Apply → Pass qualification(s) → Join a project → Complete tasks → Get paid Project time expectations For this project, tasks are estimated to require around 10–20 hours per week during active phases, based on project requirements. This is an estimate, not a guaranteed workload, and applies only while the project is active. Compensation On this project, contributors can earn up to $35 per hour equivalent, depending on their level and pace of contribution. Compensation varies across projects depending on scope, complexity, and required expertise. Please note that other projects on the platform may offer different earning levels based on their requirements.
Statistics & Python Expert - Freelance AI Trainer
Mindrift
What this opportunity involvesDesign original computational statistics problems that simulate real mathematical research workflows;Create problems requiring Python programming to solve (using Numpy, SciPy, Sympy);Ensure problems are computationally intensive and cannot be solved manually within reasonable timeframes (days/weeks);Develop problems requiring non-trivial reasoning chains in areas like number theory, combinatorics, graph theory, and numerical analysis;Base problems on real research challenges or practical applications from mathematical practice;Verify solutions using Python with standard mathematical libraries;Document problem statements clearly and provide verified correct answers.What we look forDegree in Statistics or related fields;Python proficiency for numerical validation. MATLAB, R, C, SQL, Numpy, Pandas, SciPy, domain-specific libraries, Stata or knowledge of any programming language can be equivalent;2+ years of professional experience: applied, research, or teaching experience is applicable;Strong written English (C1+);Professional certifications (e.g., CMME, SAS Certifications, CAP) and experience in international or applied projects are an advantage.How it worksApply → Pass qualification(s) → Join a project → Complete tasks → Get paidProject time expectationsFor this project, tasks are estimated to require around 10–20 hours per week during active phases, based on project requirements. This is an estimate, not a guaranteed workload, and applies only while the project is active.CompensationOn this project, contributors can earn up to $39 per hour equivalent, depending on their level and pace of contribution.Compensation varies across projects depending on scope, complexity, and required expertise. Please note that other projects on the platform may offer different earning levels based on their requirements.
Electrical Engineer & Python Expert - Freelance AI Trainer
Mindrift
What this opportunity involves Design original computational engineering problems that simulate real engineering workflows; Create problems requiring Python programming to solve engineering calculations and simulations; Ensure problems are computationally intensive and require numerical methods or iterative solutions; Develop problems involving system design, optimization, and analysis; Base problems on real research challenges or practical applications from engineering practice; Verify solutions using Python with standard engineering libraries; Document problem statements clearly and provide verified correct answers. What we look for Degree in Electrical Engineering or related fields; Python proficiency for numerical validation. MATLAB, R, C, SQL, Numpy, Pandas, SciPy, domain-specific libraries, Stata or knowledge of any programming language can be equivalent; 2+ years of professional experience: applied, research, or teaching experience is applicable; Understanding of practical engineering constraints and approximations; Strong written English (C1+); Professional certifications (e.g., CMME, SAS Certifications, CAP) and experience in international or applied projects are an advantage. How it works Apply → Pass qualification(s) → Join a project → Complete tasks → Get paid Project time expectations For this project, tasks are estimated to require around 10–20 hours per week during active phases, based on project requirements. This is an estimate, not a guaranteed workload, and applies only while the project is active. Compensation On this project, contributors can earn up to $37 per hour equivalent, depending on their level and pace of contribution. Compensation varies across projects depending on scope, complexity, and required expertise. Please note that other projects on the platform may offer different earning levels based on their requirements.