Remote Research Engineer: Code Gen & Model Eval

AuraOne; United States; On-site; USD 69,000 - 117,000; Full time

Job summary

AuraOne is seeking a Research Engineer - Code Generation & Model Evaluation for a remote contractor role in the United States. You will evaluate production code, reproduce failures, and write minimal failing tests to illustrate defects, guiding the modeling team toward fixes.

You will grade model outputs for correctness, style, and edge-case handling, document recurring failures, and calibrate reviews against gold standards. Strong debugging, test-writing, and clear reasoning are essential.

Qualifications

• Read, run, and debug unfamiliar code for this role.
• Write concise unit tests capturing a single failure mode.
• Familiarity with a testing framework (pytest/Jest/JUnit, etc.).
• Clear written reasoning to convince senior engineers.
• Reliable async availability for at least 10 hours per week.

Responsibilities

• Run and reproduce candidate code outputs in a sandboxed environment.
• Grade solutions for correctness, style, and edge-case handling.
• Write the smallest failing test demonstrating a bug.
• Compare paired solutions and rank with a written rationale.
• Tag failure modes with severity scores.
• Document recurring code-generation failures.
• Calibrate reviews against gold-standard.

Skills

Code review

Debugging

Unit testing

Engineering judgment

AI model evaluation

Model generation review

Tools

pytest

Jest

JUnit

Go test

RSpec

Job description

AuraOne is seeking a Research Engineer - Code Generation & Model Evaluation for a remote contractor role in the United States. You will evaluate production code, reproduce failures, and write minimal failing tests to illustrate defects, guiding the modeling team toward fixes.

You will grade model outputs for correctness, style, and edge-case handling, document recurring failures, and calibrate reviews against gold standards. Strong debugging, test-writing, and clear reasoning are essential.