Full-Stack React Engineer | $75/hr | Remote

About the role

We are seeking experienced senior full-stack engineers, React developers, software testing specialists, and automation engineers to build secure coding environments used to evaluate advanced AI agents. You will work with realistic website clones, identify bugs, write technical specifications, and develop automated grading systems that determine whether AI-generated code correctly solves complex software engineering tasks.

Responsibilities

• Review realistic web application clones and identify bugs, missing functionality, and workflow gaps
• Write detailed technical specifications for complex full-stack coding tasks
• Build comprehensive automated test suites for AI-generated code
• Design grading logic that produces accurate and deterministic pass or fail outcomes
• Test frontend, backend, API, database, authentication, and application-state behavior
• Identify shortcuts, exploits, hidden dependencies, and ways an AI agent could bypass intended requirements
• Strengthen evaluation environments so grading cannot be easily manipulated
• Debug unreliable tests, race conditions, asynchronous failures, and edge cases
• Review how AI agents interact with tasks and improve the evaluation methodology
• Create reproducible, isolated, and maintainable development environments
• Document expected behavior, test coverage, assumptions, and reference solutions

Who Can Apply

Relevant backgrounds include:

• Senior Full-Stack Engineers, Full-Stack Software Engineers, Senior Software Engineers, Staff Software Engineers, Principal Software Engineers, Lead Software Engineers, Full-Stack Developers, Web Application Engineers, Product Engineers, Application Developers, and Software Development Consultants
• Frontend and React backgrounds: Senior React Developers, React Engineers, Frontend Engineers, Senior Frontend Engineers, JavaScript Engineers, TypeScript Engineers, UI Engineers, Web Engineers, React Architects, Frontend Architects, Design Systems Engineers, and Client-Side Application Engineers
• Backend and platform backgrounds: Backend Engineers, Node.js Engineers, API Engineers, Platform Engineers, Infrastructure Engineers, Systems Engineers, Cloud Engineers, Developer Productivity Engineers, Developer Experience Engineers, DevOps Engineers, and Site Reliability Engineers
• Testing and quality backgrounds: QA Automation Engineers, SDETs, Software Development Engineers in Test, Test Automation Engineers, Quality Engineers, Software Test Engineers, UI Automation Engineers, End-to-End Test Engineers, Browser Automation Engineers, Test Infrastructure Engineers, Test Framework Engineers, QA Architects, Test Architects, and Quality Engineering Leads
• Security and evaluation backgrounds: Application Security Engineers, Web Security Engineers, Product Security Engineers, Penetration Testers, Security Researchers, Red Team Engineers, Secure Coding Specialists, AI Evaluation Engineers, Model Evaluation Specialists, Benchmark Engineers, AI Safety Engineers, and Human Data Specialists

Requirements

• Senior-level professional experience in full-stack software engineering
• Deep hands-on experience building web applications with React
• Strong JavaScript or TypeScript skills
• Experience developing or maintaining backend services, APIs, and databases
• Strong experience with automated testing and browser-based test frameworks
• Ability to write detailed technical specifications and acceptance criteria
• Strong debugging and code-review skills
• Understanding of test isolation, reproducibility, deterministic execution, and reliable assertions
• Ability to anticipate edge cases, unintended behaviors, and potential evaluation bypasses
• Strong written communication and attention to technical detail
• Availability for an ongoing, high-commitment remote engagement

Preferred Background

• Experience designing end-to-end testing frameworks
• Experience reviewing AI-generated code or evaluating coding agents
• Background in web security, application security, or secure test design
• Experience building coding benchmarks, technical assessments, or automated grading platforms
• Experience testing realistic website clones or complex production applications
• Experience with sandboxed execution environments and containerized applications
• Experience creating golden reference implementations or reference solutions
• Experience reviewing the work of other senior engineers