Senior Software Engineer - AI Agent Evaluation
- Role
- Fullstack
- Experience
- Senior
- Employment
- Contract
Open to CA only. Set where you work from to check your eligibility.
No BS summary
Senior software developer with 5+ years, strong Python/FastAPI, JavaScript/TypeScript/React, Docker, Postgres, Kafka, Redis, and test-writing experience. Must have B2+ English and be able to design realistic coding-agent evaluation tasks rather than just write production code. Project-based remote opportunity listed for Canada.
Required skills
Required languages
Please submit your CV in English and indicate your level of English proficiency.
Mindrift 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.
What this opportunity involves
We're building a dataset to evaluate AI coding agents - how well a model handles real-world developer tasks.
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
What this is NOT
- Not data labeling
- Not prompt engineering
- Not writing code from scratch - the agent writes most of the code; you guide and evaluate
What we look for
- 5+ years in software development
- Core stack: Python (FastAPI), JavaScript/TypeScript (React), Docker, Postgres, Kafka, Redis
- Experience writing tests (functional, integration)
- English proficiency - B2+
Why this is hard
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.
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.
Compensation
Up to $50/hr equivalent, depending on level and pace. Tasks are estimated at ~20 hours each; you set your own schedule.
What you'll do
- Build realistic developer environments with codebase, infrastructure, tickets, docs, conversations, and development history
- Design tasks from intermediate states of simulated environments
- Craft prompts and define what solved means for AI coding-agent tasks
- Ensure tasks are solvable by an AI agent
- Write tests that verify agent solutions and accept valid approaches while rejecting incorrect ones
- Iterate on tasks and tests based on QA feedback
- Review agent solutions, analyze failures, and refine evaluations until fair and robust
What they require
- 5+ years in software development
- Experience writing tests, including functional and integration tests
- English proficiency at B2+ level
- Ability to understand where frontier coding models fail and design scenarios that reveal solution quality
- Tasks must be submitted by the deadline and meet acceptance criteria
Benefits
- Choose when and how to work
- Project-based AI opportunities
- Get paid per completed project tasks
Toloka AI supports frontier model post-training by building domain-specific reinforcement learning environments, tasks, and evaluation frameworks designed by real practitioners. Mindrift, powered by Toloka, connects top domain experts with cutting-edge AI initiatives.