Senior Code Quality Engineer | AI/LLM

Crossing Hurdles; United States; Remote; USD 140,000 - 210,000; Full time

Job summary

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.

Qualifications

• 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.

Responsibilities

• 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.

Skills

Python

JavaScript/TypeScript

Java

C++

Go

C#

Ruby

PHP

Rust

Code review

Job description

Role & Responsibilities

• Review and evaluate AI-generated code for correctness, reliability, security, scalability, readability, and maintainability.
• Identify bugs, logical errors, incomplete implementations, edge-case failures, and architectural issues.
• Analyze unfamiliar codebases and assess the impact of proposed changes.
• Review bug fixes, feature implementations, refactoring, API integrations, database operations, and configuration changes.
• Compare alternative implementations and determine which solution best meets technical requirements.
• Rewrite or improve code to create high-quality reference solutions.
• Provide clear technical explanations for identified issues and recommended improvements.
• Create technical annotations, evaluation criteria, and rubrics for code-quality assessment.
• Collaborate with AI researchers and engineering teams to improve coding benchmarks and LLM evaluation.
• Apply practical software engineering judgment to assess AI-generated implementations.

Important: This is a code quality and engineering evaluation role, not a traditional software testing or manual QA position.

Preferred Candidate Profile

• 7+ years of professional software engineering experience.
• Strong proficiency in at least one programming language such as Python, JavaScript/TypeScript, Java, C++, Go, C#, Ruby, PHP, or Rust.
• Experience building, maintaining, debugging, and reviewing production-grade software.
• Strong understanding of software design principles, clean code, modular architecture, abstraction, error handling, and maintainability.
• Ability to identify functional, performance, security, and design issues in complex codebases.
• Strong debugging, root-cause analysis, and problem-solving skills.
• Experience with code reviews and collaborative software development workflows.
• Familiarity with Git and modern engineering practices.
• Good understanding of data structures, algorithms, APIs, databases, and application architecture.
• Strong written English and ability to communicate technical feedback clearly.