AI Code Evaluation Specialist

About the Opportunity Artificial Intelligence can already generate software. The challenge now is helping AI distinguish between code that merely works and code that is elegant, scalable, secure, and production-ready. We are building a network of experienced software engineers who will evaluate AI-generated code, review technical solutions, and help improve the reasoning capabilities of frontier AI models. If you're someone who naturally spots design flaws, performance bottlenecks, security risks, and cleaner implementation approaches during code reviews, this opportunity is built for you. Your expertise will directly influence how future AI systems understand software engineering best practices.

Why Join Us? ✔ Influence the future of AI software development ✔ Solve intellectually challenging engineering problems ✔ Work completely remotely ✔ Flexible, project-based assignments ✔ Earn based on expertise and contribution ✔ Collaborate on projects supporting leading AI organizations

Engagement Model This is

not a permanent employment opportunity. You'll join our

AI Expert Network as an independent contract contributor. Projects are assigned based on customer demand, technical expertise, previous quality scores, and your availability. You have complete flexibility to accept assignments that fit your schedule.

Your Mission You'll evaluate AI-generated software solutions for:

• Functional correctness
• Code quality
• Readability
• Scalability
• Security
• Maintainability
• Performance
• Architectural decisions
• Technical reasoning Assignments may include:
• Reviewing multiple AI-generated solutions
• Ranking implementation quality
• Identifying defects and hidden bugs
• Providing expert engineering feedback
• Explaining why one solution is superior
• Improving benchmark datasets

Required Skills

• 6+ years Software Development
• Strong Python or Java or Go or C++
• Excellent code review skills
• Strong Software Design knowledge
• Object-Oriented Programming
• Design Patterns
• Unit Testing
• Git

Preferred AI Experience Experience in:

• SWE-Bench
• RLHF
• HumanEval
• AI Code Evaluation
• LLM Evaluation
• AI Training Projects

No prior benchmark experience? That's perfectly fine. If you're an experienced software engineer with exceptional analytical ability and can quickly learn evaluation frameworks, we'd love to hear from you.

Who Will Thrive?

• Senior Developers
• Technical Leads
• Staff Engineers
• Engineering Managers who still enjoy reviewing code
• Architects

Join Our AI Expert Network Great engineers write code. Exceptional engineers teach AI how to recognize great code.