AI Evaluation Scenarios Engineer - Project-Based

Mindrift; Remote; ZAR 200 000 - 300 000; Part time

Job summary

A tech staffing agency is looking for software engineers for project-based AI testing roles. Ideal candidates should have over 3 years of Python development experience and skills in creating structured test cases. This opportunity offers flexibility in work hours, with tasks expected to take 6-10 hours to complete. Pay rates vary, reaching up to $24/hour depending on expertise. English proficiency at B2 level is also required. Join a fast-paced environment focused on enhancing AI systems while working remotely.

Qualifications

• 3+ years of software development experience, ideally focused on Python.
• Experience with version control using Git.
• Comfortable with structured formats like JSON/YAML.

Responsibilities

• Create structured test cases simulating human workflows.
• Define gold-standard behavior for evaluating actions.
• Analyze agent logs and decision paths.

Skills

Software development

Python

Git

JSON/YAML

Understanding core LLM limitations

Docker

Job description

A tech staffing agency is looking for software engineers for project-based AI testing roles. Ideal candidates should have over 3 years of Python development experience and skills in creating structured test cases. This opportunity offers flexibility in work hours, with tasks expected to take 6-10 hours to complete. Pay rates vary, reaching up to $24/hour depending on expertise. English proficiency at B2 level is also required. Join a fast-paced environment focused on enhancing AI systems while working remotely.