Senior Software Engineer - AI Code Evaluation

About GramianGramian 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 RoleWe 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+ yearsKey ResponsibilitiesReview and evaluate AI-generated code across programming languages and software engineering scenariosAssess code for correctness, reliability, security, scalability, readability, and maintainabilityIdentify bugs, logical errors, incomplete implementations, edge-case failures, and architectural weaknessesAnalyze unfamiliar codebases and understand the impact of proposed changesReview bug fixes, feature implementations, refactoring, API integrations, configuration changes, and database operationsCompare alternative implementations and determine whether they satisfy technical requirementsRewrite or improve code to create high-quality reference solutionsProvide clear technical explanations of identified issues and recommended improvementsDevelop evaluation criteria, technical annotations, and rubrics for code-quality assessmentCollaborate with researchers and engineering teams to design coding benchmarks and improve LLM evaluation methodologiesRequirements7+ years of professional software engineering experienceStrong proficiency in at least one programming language, including Python, JavaScript/TypeScript, Java, C++, Go, C#, Ruby, PHP, or RustSignificant experience building, maintaining, debugging, and reviewing production-grade softwareStrong understanding of software design principles, clean code, modular architecture, abstraction, error handling, and maintainabilityProven ability to identify functional, performance, security, and design issues in complex codebasesStrong debugging, root-cause analysis, and problem-solving skillsExperience with code reviews and collaborative software development workflowsFamiliarity with Git and modern software engineering practicesStrong written English and ability to communicate technical feedback clearlyGood understanding of data structures, algorithms, APIs, databases, and application architecture