Java Software Engineer for AI Code Evaluation (Contract)

Turing; Greater London; On-site; GBP 47,000 - 83,000; Part time

Benefits offered by this job

Flexible schedule

Contractor engagement

Job summary

Turing is seeking a Software Engineering evaluator to curate datasets for training and benchmarking large language models. You will work with researchers to refine code primarily in Java, with Python, JavaScript (ReactJS), C/C++, Rust, and Go, evaluating AI-generated code for efficiency and reliability.

This flexible contractor role requires 10–40 hours/week, with a one-month duration and potential extension, and is open to candidates based in US, Canada or WEU regions.

Qualifications

• Several years of software engineering experience (3+ years).
• Strong understanding of full-stack development and scalable production-grade software.

Responsibilities

• Curate code examples and build solutions for AI model training and benchmarking.
• Evaluate and refine AI-generated code for efficiency, scalability, and reliability.
• Write precise evaluation rationales and document findings clearly.
• Collaborate with researchers and cross-functional teams to improve coding solutions.

Skills

Software engineering experience

Full-stack development

Code quality and reviews

Clear written/oral communication

Tools

Java

Python

JavaScript/ReactJS

C/C++

Rust

Go

Job description

Turing is seeking a Software Engineering evaluator to curate datasets for training and benchmarking large language models. You will work with researchers to refine code primarily in Java, with Python, JavaScript (ReactJS), C/C++, Rust, and Go, evaluating AI-generated code for efficiency and reliability.

This flexible contractor role requires 10–40 hours/week, with a one-month duration and potential extension, and is open to candidates based in US, Canada or WEU regions.