Senior Software Engineer (Remote) – AI Task Design & Evaluation

Synthires; California; À distance; USD 165 000 - 248 000; Temps partiel

Résumé du poste

Synthires is seeking a Senior Software Engineering Expert for a remote engagement to help improve AI systems' real-world software engineering capabilities. You will design challenging tasks, develop reference solutions, and evaluate AI-generated code using your expertise.

Responsibilities include designing tasks, explaining complexity, creating tests, evaluating code, and providing evidence-based assessments while incorporating reviewer feedback to refine submissions.

Qualifications

• 4+ years of professional software engineering experience at a leading technology company, quantitative firm, financial institution, or high-growth tech company.
• Experience with system design, testing, debugging, code review, and large production codebases.
• Ability to evaluate code quality beyond whether tests pass and to explain trade-offs clearly.
• Excellent written English and the ability to communicate technical decisions clearly.

Responsabilités

• 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, architecture, maintainability, style, and scope.
• Evaluate AI-generated code and collaborate with AI agents to assess strengths and weaknesses.
• Provide consistent, evidence-based assessments of engineering quality.
• Incorporate reviewer feedback and refine submitted work.

Connaissances

Python

Java

C++

Go

TypeScript

Rust

Formation

Bachelor's degree from an English-speaking country

Description du poste

Synthires is seeking a Senior Software Engineering Expert for a remote engagement to help improve AI systems' real-world software engineering capabilities. You will design challenging tasks, develop reference solutions, and evaluate AI-generated code using your expertise.

Responsibilities include designing tasks, explaining complexity, creating tests, evaluating code, and providing evidence-based assessments while incorporating reviewer feedback to refine submissions.