Senior Software Engineer — AI Code Evaluator (Remote)

Synthires; Greater London; Remote; GBP 123,000 - 185,000; Part time

Job summary

Synthires is seeking a Senior Software Engineering Expert for a remote hourly contract. You will design challenging software engineering tasks, develop reference solutions, and rigorously evaluate AI-generated code using your senior engineering judgment.

You will lead reviews, define evaluation criteria, and provide actionable feedback to improve system design, testing, and code quality. Strong English communication is essential.

Qualifications

• Four+ years of professional software engineering experience at leading tech or finance firms.
• Senior-level or mid-senior experience, depending on employer.
• Strong programming language proficiency (Python/Java/C++/Go/TypeScript/Rust).
• Experience with system design, testing, debugging, code review, and large production codebases.
• Ability to evaluate code quality beyond tests, and to explain trade-offs clearly.
• Excellent written English and clear presentation of decisions.

Responsibilities

• Design realistic software engineering tasks involving feature development, debugging, code review, system design, and documentation.
• Explain task complexity, verification methods, and real-world relevance.
• Create reference solutions, tests, and evaluation criteria for correctness and maintainability.
• Evaluate AI-generated code and collaborate with AI coding agents to assess strengths and weaknesses.
• Provide consistent, evidence-based assessments of engineering quality.
• Incorporate reviewer feedback and refine submitted work.

Skills

Python

Java

C++

Go

TypeScript

Rust

Education

Bachelor's degree from an English-speaking country

Job description

Synthires is seeking a Senior Software Engineering Expert for a remote hourly contract. You will design challenging software engineering tasks, develop reference solutions, and rigorously evaluate AI-generated code using your senior engineering judgment.

You will lead reviews, define evaluation criteria, and provide actionable feedback to improve system design, testing, and code quality. Strong English communication is essential.