Full Stack Engineer

Turing • San Francisco, CA

3d

About The Position

As a Software Engineering evaluator, you will create datasets for training, benchmarking, and advancing large language models in close collaboration with researchers. The work involves curating code examples, providing precise solutions, and correcting code, primarily in Python across backend services, data pipelines, and ML infrastructure, as well as in JavaScript (including ReactJS), C/C++, Java, Rust, and Go. You will evaluate and refine AI-generated code for efficiency, scalability, and reliability, and collaborate with cross-functional teams to improve enterprise-level AI coding solutions.

The role also involves building Python agents and automated verification tools to assess code quality and identify error patterns; evaluating model capabilities across stages of the software engineering cycle; and designing mechanisms to automatically verify solutions to software engineering tasks. The engagement is contractor work for one month, with potential extensions based on performance and fit. Candidates must be based in the United States. The commitment is flexible, from a minimum of 10 hours per week up to 40 hours per week.

Requirements

• At least 3 years of software engineering experience.
• Strong expertise in Python, including frameworks, tooling, and best practices for production-grade software.
• Experience building full-stack applications and deploying scalable software using modern languages and tools.
• Deep understanding of software architecture, design, development, debugging, and code quality and review assessment.
• Excellent oral and written communication skills for providing clear, structured evaluation rationales.
• Must be based in the United States.

Nice To Haves

• Experience building production systems at Google, Microsoft, Apple, Amazon, Meta, or similar high-scale engineering organizations.
• Graduation from a top computer science program such as Stanford, MIT, Carnegie Mellon, UC Berkeley, Georgia Tech, or a comparable institution; exceptional experience and skill take precedence over pedigree.

Responsibilities

• Curate code examples, develop precise solutions, and correct code for AI model training initiatives, primarily in Python and also in JavaScript (including ReactJS), C/C++, Java, Rust, and Go.
• Evaluate and refine AI-generated code to ensure efficiency, scalability, and reliability.
• Collaborate with cross-functional teams to improve AI-driven coding solutions against industry performance benchmarks.
• Build Python agents and automated verification tools to assess code quality and identify error patterns.
• Hypothesize about and evaluate model capabilities across software engineering stages, including prototyping, architecture and API design, production implementation, launch, experiments, monitoring, and operational maintenance.
• Design mechanisms that automatically verify solutions to software engineering tasks.

What This Job Offers

• Career Level: Mid Level
• Education Level: No Education Listed