Software Engineer – AI Evaluation Specialist

Alignerr is seeking experienced software engineers to evaluate and improve frontier AI models. The role involves applying engineering expertise to identify failure modes, assess model limitations, and provide structured feedback on AI-generated code.

Responsibilities:

• Evaluate the performance of frontier language models on complex software engineering tasks
• Identify bugs, logical errors, hallucinations, and reliability issues in model outputs
• Design and review prompts, test cases, and evaluation scenarios for advanced coding workflows
• Provide precise written feedback explaining model strengths, weaknesses, and edge cases
• Work across multiple languages and codebases to assess generalization and correctness

Requirements:

• 3–4+ years of professional software engineering experience
• Strong proficiency in at least one of: TypeScript, Ruby, Java, or C++
• Excellent written and spoken English
• Demonstrated ability to reason about complex systems and debug non-obvious issues
• Familiarity with modern AI / LLM tooling (Git, CLI workflows, testing frameworks, etc.)
• Ability to critically evaluate model behavior rather than simply use model outputs