Backend Software Engineer (Contract)

Quick Facts

• Role: Backend Software Engineer (Contract)

• Work model: Project-based, fully remote

• Commitment: ~15 hours/week

• Compensation: Output-based, paid per approved task

• Time per task: 5 hours for trainers; 1.5 hours for reviewers

Description

You will create Reinforcement Learning environments that test a model’s ability to solve real software engineering problems—finding subtle bugs, implementing non-trivial features, refactoring, and optimizing performance. Each task involves defining the problem, creating a reproducible environment, and providing a reference solution.

Responsibilities

• Create realistic, challenging coding tasks drawn from repositories you know well

• Design tasks that require real engineering skill (subtle bugs, meaningful performance work), not lookup or boilerplate

• Build a reproducible environment for each task

• Write deterministic verifiers that validate correct solutions across valid implementations and reject incorrect/partial/hard-coded approaches

• Provide a reference solution demonstrating how the task can be solved

• Flag tasks that are ambiguous or unverifiable

Requirements

• Hands-on expertise in at least one of Python3, Java, Rust, Go, C++, or TypeScript

• Deep understanding of algorithms, data structures, and software engineering principles

• Proven ability to debug complex systems, resolve bugs, and deliver effective optimizations

• Experience with large codebase refactoring and legacy system modernization

• Track record of delivering high-impact features from conception through delivery

• Strong documentation and communication skills

• Interest in AI and its technical challenges (previous AI experience not required)

Benefits

• Fully remote, project-based work

• Paid per approved task with time varying by task type and your experience