Software Engineer - Java

Turing • Austin, TX

14h

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. You will curate code examples, provide solutions, and correct code primarily in Java, as well as Python, JavaScript (including ReactJS), C/C++, Rust, and Go. You will evaluate and refine AI-generated code for efficiency, scalability, and reliability, and work with cross-functional teams to improve enterprise-level AI-driven coding solutions.

The work also involves building agents to verify code quality and identify error patterns; hypothesizing about steps across the software engineering cycle and evaluating model capabilities at those steps; and designing mechanisms that can automatically verify solutions to software engineering tasks.

This is a flexible contractor engagement requiring a minimum of 10 hours per week and allowing up to 40 hours per week. The initial duration is one month, with potential extensions based on performance and fit. Candidates must be based in the US, Canada, or specified Western European countries. The application process takes 15–30 minutes and requires completion of an AI video interview.

Requirements

• At least 3 years of software engineering experience.
• Strong expertise building full-stack applications and deploying scalable, production-grade 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 US, Canada, or the listed Western European countries.

Responsibilities

• Create datasets for training, benchmarking, and advancing large language models in collaboration with researchers.
• Curate code examples, provide solutions, and correct code, primarily in Java and also in Python, JavaScript (including ReactJS), C/C++, Rust, and Go.
• Evaluate and refine AI-generated code for efficiency, scalability, and reliability.
• Collaborate with cross-functional teams to improve AI-driven coding solutions against industry performance benchmarks.
• Build agents that verify code quality and identify error patterns.
• Hypothesize about steps in the software engineering cycle and evaluate model capabilities across them.
• Design mechanisms that automatically verify solutions to software engineering tasks.

What This Job Offers

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