Back to all jobs
Visible on IKONS todayNewPopular
LiegeRemote30 hours/week<3months
A technology company connects specialists with project-based AI opportunities for leading tech companies, focused on testing, evaluating, and improving AI systems.
- Participation is project-based, not permanent employment.
- We're building a dataset to evaluate AI coding agents – how well a model handles real-world developer tasks.
- Tasks for this project are estimated to take 30 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.
- Paid per accepted task. Your rate depends on the qualification tier you reach and how efficiently you complete tasks – up to the equivalent of $200/hr.
What you do
- You'll create challenging tasks and evaluation criteria within realistic simulated environments:
- Build realistic developer environments – a virtual company with codebase, infrastructure, and context (tickets, docs, conversations) that forms a believable development history.
- Design tasks from intermediate states of these environments – craft the prompt, define what 'solved' means, and ensure the task is solvable by an AI agent.
- Write tests that verify agent solutions – accept all valid approaches and reject incorrect ones, neither too strict nor too lenient.
- Iterate on tasks and tests based on QA feedback – review agent solutions, analyze failures, and refine until the evaluation is fair and robust.
- This is NOT data labeling, NOT prompt engineering, NOT writing code from scratch – the agent writes most of the code; you guide and evaluate.
What they ask
- 8+ years in software development.
- Core stack: Python (FastAPI), JavaScript/TypeScript (React), Docker, Postgres, Kafka, Redis.
- Experience writing tests (functional, integration).
- English proficiency: B2+.
Profile
- Frontier models are already good at coding. Creating a task that genuinely challenges the best models is non-trivial.
- You need to deeply understand where models fail and what scenarios reveal the difference between a good and a bad solution.
- Tasks have many valid solutions – writing tests that accept all correct solutions and reject incorrect ones is harder than it sounds.
Practical
- Flexible Work Hours: you choose when and how to work.
- Fully remote role.
How to apply
View the full assignment text and application details once your tailored application is ready.
Order a tailored application to view the full assignment and application details.
More context, less searching.
You get enough context to judge whether this job is relevant. The full brief, client details and next steps stay available inside the app.