Contract work that fits your background — steady projects, hours you set, and expert rates from $75–$125+/hr. Fully remote.
Remote · Canada
Evaluate AI-generated frontend implementations by testing components, state management, accessibility, rendering, and end-to-end web features. Identify UX and correctness failures, then write robust implementations that handle edge cases and real-world content.
Remote · Canada
Use frontier AI models to build end-to-end application features spanning the frontend, API, and database, then evaluate how well the implementation works. Diagnose failures across application layers and write robust working solutions and clear judgments to help train AI models.
Remote · Canada
Evaluate AI-generated analyses on real datasets, checking method selection, assumptions, statistical validity, and whether conclusions follow from the data. Identify flawed reasoning and write rigorous replacement analyses with clear takeaways and honest uncertainty.
Remote · Canada
Use frontier AI models to complete real engineering tasks, then assess their code and reasoning against production standards. Red-team model outputs to uncover bugs, unsafe code, fabricated test results, and incorrect solutions, and document findings to improve coding agents.
Remote · Canada
Evaluate AI models' reasoning about CI/CD, infrastructure-as-code, containers, and cloud operations, identifying unsafe or unreliable automation. Write correct approaches that clearly explain failure modes and recovery.