Senior Software Engineer, Reinforcement Learning

You will create reproducible reinforcement learning environments that test how AI models solve complex software engineering workflows. Your work will cover DevOps, CI/CD, debugging, and command-line tools such as Git, Docker, GDB, AddressSanitizer, and FFmpeg.

You will also create realistic software engineering scenarios, produce golden reference solutions that show reliable ways to complete tasks, and assess solutions using sound judgment about algorithms, data structures, maintainability, performance, and scalability.

• Design tasks that evaluate AI models on DevOps, CI/CD, and debugging problems.
• Build or refine reproducible reinforcement learning environments and realistic software workflows.
• Use command-line development and debugging tools, including Git, Docker, GDB, AddressSanitizer, and FFmpeg.
• Create golden reference solutions for the workflows and tasks you develop.

Work is available in the listed countries, subject to applicable hiring eligibility.

• $80 to $120 per hour equivalent, paid per task that meets project specifications.
• Expected commitment: approximately 15 hours per week.
• Proficiency in one or more of C++, Python, Java, Go, TypeScript, or Rust.
• Strong understanding of algorithms, data structures, and performance tuning.
• Ability to debug complex software issues and deliver maintainable solutions.
• Experience with feature development, codebase refactoring, and performance optimization.
• Strong written and verbal communication, close attention to detail, and effective collaboration in remote or cross-functional settings.
• Prior AI experience is not required when you bring strong software engineering expertise.