Senior SWE Code Reviewer — Remote Contractor

AuraOne; United States; On-site; USD 207,000 - 289,000; Full time

Job summary

AuraOne is seeking an Expert Senior SWE to join a remote engineering review track that evaluates production code, debugs traces, and reviews developer-facing AI outputs for correctness. You will reproduce failures in a sandbox and explain the fix so the modeling team can target the gap.

You will write minimal failing tests, grade solutions for correctness and edge cases, tag failure modes with severity, and document recurring issues to help improve future reviews.

Qualifications

• Strong day-job engineering experience with ability to read, run, and debug unfamiliar code.
• Ability to write concise unit tests that capture a single failure mode.
• Familiarity with a testing framework (pytest/Jest/JUnit, etc.).
• Clear written reasoning to convince other senior engineers.
• Reliable async availability for at least 10 hours per week.
• Prior code-review or technical-interview-grading experience is a plus.

Responsibilities

• Run and reproduce candidate code outputs in a sandboxed environment.
• Grade senior SWE solutions for correctness, 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

Software engineering judgment

Senior SWE engineering review

Tools

Testing frameworks

Job description

AuraOne is seeking an Expert Senior SWE to join a remote engineering review track that evaluates production code, debugs traces, and reviews developer-facing AI outputs for correctness. You will reproduce failures in a sandbox and explain the fix so the modeling team can target the gap.

You will write minimal failing tests, grade solutions for correctness and edge cases, tag failure modes with severity, and document recurring issues to help improve future reviews.