Backend Software Engineer (Contract, Remote)

Quick Facts

• Role: Backend Software Engineer (Contract)
• Work setup: Remote
• Commitment: ~15 hours/week
• Engagement: Project-based; paid per approved task

Description

You’ll create Reinforcement Learning environments that test a model’s ability to solve real software engineering problems, including tracking down subtle bugs, building non-trivial features, refactoring, and optimizing performance. Each task means defining the problem, building a reproducible environment, and writing a reference solution.

Role Responsibilities

• Build challenging coding problems from real repositories with reproducible environments and verifiers
• Create realistic, challenging coding tasks for frontier AI models
• Design problems that require genuine engineering skill (subtle bugs, non-trivial features, meaningful performance work)
• Build a reproducible environment for each task
• Write deterministic verifiers that accept correct solutions across different valid implementations and reject incorrect, incomplete, or hard-coded approaches
• Provide a reference solution showing how the task can be solved
• Flag tasks that are ambiguous or unverifiable

Requirements

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

Preferred Qualifications

• Significant 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 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)

Compensation & Start

• Output-based compensation: paid per task that meets project specifications (time may vary)
• Typically filled within 48 hours; expected to start first tasks within 24–48 hours of onboarding