[Hiring] Software Engineer @Athyna

Role Description

Hey there! We're looking for a Software Engineer to join our Intelligence team and build Terminal-Bench 4 (TB4) tasks, on a task-based contract. If you are detail-oriented, self-driven, and hands-on with Linux and Docker, keep reading!

• 100% Remote
• Paid in USD per task
• LATAM - Reporting to a fully async team
• Task-based contract
• Advanced English

In your day-to-day, you will:

• Design and build TB4 tasks following the project guidelines and the task templates
• Complete a paid trainee task first, then move on to the main project once it is approved
• Submit each task as a pull request on a private GitHub repo and work with reviewers on feedback
• Ask and answer task-specific questions directly in the PR so the history stays with the task
• Iterate on your tasks within the 3-version limit until they are approved (many first versions get solved by the model, so iterating is part of the job)
• Write the task instructions yourself, without AI help

Qualifications

• 3+ years of professional experience as a software engineer
• Deep expertise in at least one technical area (databases and storage, compilers, distributed systems, networking, security, numerical code, or build systems), including the subtle mistakes experts make there
• Precise technical writing: you can state every requirement without giving the solution away
• A tester's mindset: you find shortcuts and edge cases
• Strong command of the Linux terminal and shell workflows
• Hands-on experience with Docker and containerized environments
• Comfortable with Git and GitHub pull request workflows
• Ability to work independently and async, with clear written communication in English

Requirements

• Experience writing automated tests (for example, pytest) or validation scripts
• Previous work on AI evaluation, benchmarks, or AI training data
• Experience with Python scripting and debugging complex environments