Software Engineering AI Evaluator

Evaluate AI-generated software with Python, JavaScript, and full-stack expertise for Turing’s frontier AI research initiatives. This contractor engagement requires partial PST overlap.

As a Software Engineering evaluator, you will create datasets for training and benchmarking large language models with researchers. You will curate code, provide precise solutions, correct implementations, and assess AI-generated software. The work spans architecture, development, debugging, and code quality across modern languages and tools.

Key Responsibilities:

• Curate code examples for AI model training initiatives
• Correct Python, JavaScript, C/C++, Java, Rust, and Go code
• Evaluate AI-generated code for efficiency and reliability
• Build agents identifying code quality and error patterns
• Design automated verification mechanisms for software solutions

Requirements:

• Three or more years of software engineering experience
• Expertise building full-stack, production-grade scalable applications
• Understanding of architecture, design, development, debugging, and code review
• Excellent oral and written communication for evaluation rationales
• Residence in the United States, Canada, or specified WEU countries

Apply software architecture, full-stack development, and code evaluation expertise to advance Turing’s AI-driven coding solutions.