Remote Frontend AI Quality Reviewer

AuraOne; United States; On-site; USD 83,000 - 165,000; Part time

Job summary

AuraOne is seeking a Frontend Engineering AI Evaluator contractor for remote work in the United States. You will reproduce and evaluate frontend AI-generated code, grade solutions for correctness and style, and write minimal failing tests to illustrate edge-case bugs.

You will compare paired solutions, justify rankings with rubric-based rationales, and document recurring failures to guide model improvements. Strong debugging, unit testing, and clear writing are essential.

Qualifications

• Strong day-job engineering experience; read, run, and debug unfamiliar code for Frontend Engineering AI Evaluator work.
• Comfort writing concise unit tests that capture a single failure mode.
• Clear, persuasive written reasoning to convince another senior engineer.

Responsibilities

• Run and reproduce candidate code outputs in a sandboxed environment for Frontend Engineering AI Evaluator assignments.
• Grade frontend engineering solutions for correctness, complexity, idiomatic style, and edge-case handling.
• Write minimal failing tests that demonstrate the bug a model output missed.
• Compare paired solutions and rank them with a written rationale tied to the rubric.
• Tag failure modes (compile error, runtime crash, off-by-one, security issue) with severity scores.
• Document recurring code-generation failures so the modeling team can target them.
• Calibrate against gold-standard reviews to keep inter-rater agreement above target.

Skills

Code review

Debugging

Unit testing

Frontend engineering

AI evaluation

Rubric writing

Expert review

Engineering judgment

Software engineering

Job description

AuraOne is seeking a Frontend Engineering AI Evaluator contractor for remote work in the United States. You will reproduce and evaluate frontend AI-generated code, grade solutions for correctness and style, and write minimal failing tests to illustrate edge-case bugs.

You will compare paired solutions, justify rankings with rubric-based rationales, and document recurring failures to guide model improvements. Strong debugging, unit testing, and clear writing are essential.