Remote Software Review Engineer for Model QA & Debugging

AuraOne Human Data; United States; A distancia; USD 165.000 - 248.000; Jornada completa

Descripción de la vacante

AuraOne Human Data is seeking a remote contractor for a Senior Software Engineering Experts review track. You will read, run, and debug production code outputs, reproduce failures, and write the minimal failing tests needed for evaluation.

You will grade solutions for correctness, style, and edge-case handling, and document recurring failures for the modeling team. The role requires strong engineering judgment, concise review notes, and reliable availability of at least 10 hours per week.

Formación

• Strong day‑job engineering experience.
• Comfort writing concise unit tests that capture a single failure mode.
• Familiarity with a testing framework such as pytest, Jest, or JUnit.
• Clear written reasoning in review notes.
• Reliable async availability for at least 10 hours per week.
• Prior code-review or technical‑interview grading experience is a plus.

Responsabilidades

• Run and reproduce candidate code outputs in a sandboxed environment for Senior Software Engineering Experts assignments.
• Grade 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 with severity scores.
• Document recurring code‑generation failures for the modeling team.
• Calibrate against gold‑standard reviews to maintain inter‑rater agreement.

Conocimientos

Code review

Debugging

Unit testing

Software engineering judgment

Senior engineering review

Herramientas

pytest

Jest

JUnit

Go test

RSpec

Descripción del empleo

AuraOne Human Data is seeking a remote contractor for a Senior Software Engineering Experts review track. You will read, run, and debug production code outputs, reproduce failures, and write the minimal failing tests needed for evaluation.

You will grade solutions for correctness, style, and edge-case handling, and document recurring failures for the modeling team. The role requires strong engineering judgment, concise review notes, and reliable availability of at least 10 hours per week.