C++ Software Engineer - AI Model Evaluation & Datasets

Turing; Austin (TX); On-site; USD 55,000 - 110,000; Full time

Job summary

Turing is seeking a Software Engineering evaluator to build and refine cutting-edge datasets for training and benchmarking large language models. You will curate code examples and provide precise solutions primarily in C/C++, and also Python, JavaScript (ReactJS), Java, Rust, and Go, evaluating AI-generated code for correctness and efficiency.

You’ll collaborate with researchers and cross-functional teams to improve enterprise-grade coding solutions, design verification mechanisms, and create

Qualifications

• 3+ years of software engineering experience.
• Strong experience building full-stack applications and deploying production-grade software.
• Deep understanding of software architecture, design, development, debugging and code quality.
• Excellent oral and written communication skills for clear evaluation rationales.

Responsibilities

• Curate code examples and provide precise solutions, primarily in C/C++, plus Python, JavaScript (ReactJS), Java, Rust and Go.
• Evaluate and refine AI-generated code for efficiency, scalability, and reliability.
• Collaborate with researchers and cross-functional teams to improve enterprise AI-driven coding solutions.
• Design verification mechanisms to automatically verify solutions to software engineering tasks.
• Hypothesize on software engineering lifecycle steps and assess model capabilities accordingly.
• Build agents that can verify code quality and identify error patterns.

Skills

Full-stack development

Software architecture

Code quality

Communication skills

Job description

Turing is seeking a Software Engineering evaluator to build and refine cutting-edge datasets for training and benchmarking large language models. You will curate code examples and provide precise solutions primarily in C/C++, and also Python, JavaScript (ReactJS), Java, Rust, and Go, evaluating AI-generated code for correctness and efficiency.

You’ll collaborate with researchers and cross-functional teams to improve enterprise-grade coding solutions, design verification mechanisms, and create