AI/LLM Code Quality Engineer: Elevate Reliability

Crossing Hurdles; United States; A distancia; USD 140.000 - 210.000; Jornada completa

Descripción de la vacante

Crossing Hurdles seeks a senior software engineer to lead the evaluation of AI-generated code for correctness, reliability, security, and maintainability. You will review complex changes, rewrite samples for clarity, and provide concrete recommendations to improve benchmarks and benchmarks for code quality.

The role requires 7+ years of experience, deep knowledge of multiple languages, and strong communication skills in English to articulate feedback to researchers and engineering teams.

Formación

• 7+ years of professional software engineering experience.
• Excellent ability to review AI-generated code for correctness, reliability, security, and maintainability.
• Strong understanding of software design principles and clean code practices.
• Fluent written English with ability to communicate feedback clearly.

Responsabilidades

• Review AI-generated code for correctness, reliability, security, and maintainability.
• Identify bugs, logical errors, incomplete implementations, and edge-case failures.
• Analyze unfamiliar codebases and assess impact of proposed changes.
• Review bug fixes, new features, refactoring, API integrations, and DB operations.
• Compare alternative implementations and select solutions meeting requirements.
• Rewrite or improve code to produce high-quality reference solutions.
• Provide clear technical explanations and recommendations.
• Create annotations, evaluation criteria, and rubrics for code quality.
• Collaborate with AI researchers and engineers to improve benchmarks.
• Apply practical software engineering judgment to evaluate AI implementations.

Conocimientos

Python

JavaScript/TypeScript

Java

C++

Go

C#

Ruby

PHP

Rust

Code review

Descripción del empleo

Crossing Hurdles seeks a senior software engineer to lead the evaluation of AI-generated code for correctness, reliability, security, and maintainability. You will review complex changes, rewrite samples for clarity, and provide concrete recommendations to improve benchmarks and benchmarks for code quality.

The role requires 7+ years of experience, deep knowledge of multiple languages, and strong communication skills in English to articulate feedback to researchers and engineering teams.