Remote AI Code Reviewer & Debugger

AuraOne; United States; On-site; USD 93,676 - 126,739; Full time

Job summary

AuraOne seeks a Project Controls Engineer to remotely review produced code and debugging traces, evaluating correctness against real-world standards. You will reproduce outputs in a sandbox, write minimal failing tests, and provide clear rationale tied to a rubric for model improvement.

Responsibilities include grading solutions for correctness and style, documenting recurring failures, and calibrating reviews against gold standards. Remote US-eligible contractor role.

Qualifications

• Strong day-job engineering experience—read, run, and debug unfamiliar code for Project Controls Engineer work.
• Comfort writing concise unit tests that capture a single failure mode.
• Familiarity with at least one of: pytest, Jest, JUnit, Go test, RSpec, or equivalent.
• Clear written reasoning—your review note has to convince another senior engineer.
• Reliable async availability for at least 10 hours per week.

Responsibilities

• Run and reproduce candidate code outputs in a sandboxed environment for Project Controls Engineer assignments.
• Grade project controls engineer engineering review 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

Software engineering judgment

Project Controls Engineer engineering

Tools

pytest

Jest

JUnit

Go test

RSpec

Job description

AuraOne seeks a Project Controls Engineer to remotely review produced code and debugging traces, evaluating correctness against real-world standards. You will reproduce outputs in a sandbox, write minimal failing tests, and provide clear rationale tied to a rubric for model improvement.

Responsibilities include grading solutions for correctness and style, documenting recurring failures, and calibrating reviews against gold standards. Remote US-eligible contractor role.