Senior Software Engineer - AI Code Evaluation

Location: Bangladesh, Brazil, Colombia, Egypt, Ghana, India

Department: Talent Solutions

Workplace: remote

Employment Type: contract

Description

About Gramian

Gramian Consultancy is a boutique consultancy specializing in IT professional services and engineering talent solutions. With a strong background in software engineering and leadership, we help companies build high-performing teams by matching them with professionals who truly fit their needs.

About the Role

We are looking for senior software engineers with 7+ years of industry experience to support the training and evaluation of large language models. You will review, analyze, and improve AI-generated code, applying real-world engineering judgment to assess correctness, security, scalability, maintainability, and production quality.

This is a software engineering and code-quality evaluation role, not a traditional software testing or manual QA position. You will analyze unfamiliar codebases, identify root causes, compare alternative implementations, and create robust solutions and evaluation criteria.

SENIORITY: Senior — 7+ years

Key Responsibilities

• Review and evaluate AI-generated code across programming languages and software engineering scenarios.
• Assess code for correctness, reliability, security, scalability, readability, and maintainability.
• Identify bugs, logical errors, incomplete implementations, edge-case failures, and architectural weaknesses.
• Analyze unfamiliar codebases and understand the impact of proposed changes.
• Review bug fixes, feature implementations, refactoring, API integrations, configuration changes, and database operations.
• Compare alternative implementations and determine whether they satisfy technical requirements.
• Rewrite or improve code to create high-quality reference solutions.
• Provide clear technical explanations of identified issues and recommended improvements.
• Develop evaluation criteria, technical annotations, and rubrics for code-quality assessment.
• Collaborate with researchers and engineering teams to design coding benchmarks and improve LLM evaluation methodologies.

Requirements

• 7+ years of professional software engineering experience.

• Strong proficiency in at least one programming language, including Python, JavaScript/TypeScript, Java, C++, Go, C#, Ruby, PHP, or Rust.
• Significant experience building, maintaining, debugging, and reviewing production-grade software.
• Strong understanding of software design principles, clean code, modular architecture, abstraction, error handling, and maintainability.
• Proven 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 software engineering practices.
• Strong written English and ability to communicate technical feedback clearly.
• Good understanding of data structures, algorithms, APIs, databases, and application architecture.