Senior Full-Stack Engineers (React): AI Evaluation Environments
Summary
Build secure, automated testing environments in React to evaluate AI-generated code submissions and prevent manipulation for an AI research partner.
This position is listed on behalf of a partner company, who manages all applications and next steps. Our partner is looking for Senior Full-Stack Engineers (React): AI Evaluation Environments based in the United States.
This is a unique opportunity for an experienced full-stack engineer to contribute to the advancement of artificial intelligence by developing sophisticated evaluation environments for coding agents. In this role, you will help build secure, reliable testing systems that accurately assess AI-generated code while preventing manipulation or shortcuts. Working remotely on long-term technical projects, you'll combine software engineering expertise with analytical thinking to create robust testing frameworks and detailed technical specifications. The position offers exposure to cutting-edge AI research, challenging engineering problems, and the chance to directly influence how next-generation AI systems are evaluated and improved.
Accountabilities
- Design, develop, and refine secure AI evaluation environments using modern full-stack development practices.
- Analyze real-world web application clones to identify bugs, workflow issues, and opportunities for improving evaluation quality.
- Write comprehensive technical specifications that define complex AI coding tasks and expected behaviors.
- Build and maintain automated testing frameworks capable of accurately evaluating AI-generated code submissions.
- Develop grading logic that is robust, reliable, and resistant to AI exploitation or unintended shortcuts.
- Collaborate on improving evaluation methodologies by identifying edge cases, testing scenarios, and system vulnerabilities.
- Apply strong engineering judgment to ensure evaluation systems remain scalable, maintainable, and technically rigorous.
- Contribute to long-term research initiatives focused on improving AI coding performance and evaluation accuracy.
- Senior-level professional experience in full-stack software engineering.
- Extensive hands-on expertise developing modern web applications using React.
- Strong experience designing and implementing automated testing frameworks and quality assurance processes.
- Proven ability to write detailed technical specifications for complex software systems.
- Deep understanding of web application architecture, debugging, and software development best practices.
- Experience with web security, AI evaluation systems, QA automation, or related technical domains is highly desirable.
- Excellent analytical and problem-solving skills with the ability to anticipate complex technical edge cases.
- Comfortable working independently in a remote, long-term contract environment.
- Strong written communication skills and attention to technical accuracy and detail.
- Competitive compensation of $75 per hour.
- Fully remote contract opportunity with flexible work location within the United States.
- Long-term technical engagement focused on innovative AI research initiatives.
- Opportunity to contribute to the development of next-generation AI evaluation systems.
- Exposure to complex engineering challenges involving AI, automated testing, and secure software evaluation.
- Collaborative environment working alongside highly skilled technical professionals.
- Opportunity to expand expertise in AI, software quality, and advanced testing methodologies.