Software Engineer - AI Data & Model Evaluation

turing; California (MO); Hybrid; USD 70,000 - 110,000; Part time

Job summary

Turing, based in San Francisco, is seeking a Software Engineering evaluator to create high-quality datasets for training and benchmarking large language models. You will curate code examples and provide precise solutions across Python, JavaScript (ReactJS), C/C++, Java, Rust, and Go, and refine AI-generated code for reliability.

As a contractor, you will collaborate with researchers and cross-functional teams, building verification mechanisms and analyzing error patterns to advance enterprise

Qualifications

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

Responsibilities

• Curate code examples and solutions across multiple languages for AI model training.
• Evaluate and refine AI-generated code for efficiency, scalability, and reliability.
• Collaborate with researchers and cross-functional teams on enterprise AI-driven coding solutions.
• Build agents to verify code quality and identify error patterns.
• Hypothesize steps in the software engineering cycle and evaluate model capabilities.
• Design verification mechanisms to automatically verify software solutions.

Skills

Software engineering

Full-stack development

Code quality & review

Effective communication

Tools

Python

JavaScript/ReactJS

C/C++

Java

Rust

Go

Job description

Turing, based in San Francisco, is seeking a Software Engineering evaluator to create high-quality datasets for training and benchmarking large language models. You will curate code examples and provide precise solutions across Python, JavaScript (ReactJS), C/C++, Java, Rust, and Go, and refine AI-generated code for reliability.

As a contractor, you will collaborate with researchers and cross-functional teams, building verification mechanisms and analyzing error patterns to advance enterprise