Remote Senior AI Software Evaluator (Python)

Turing Enterprises, Inc.; Boston (MA); À distance; USD 55 000 - 96 000; Temps partiel

Avantages offerts par ce poste

Contractor engagement (no medical/paid

Résumé du poste

Turing Enterprises, Inc. is seeking a Software Engineering evaluator to create cutting-edge datasets for training and benchmarking large language models.

You will curate code samples, provide precise solutions, and correct errors—primarily in Python across backend services, data pipelines, and ML infrastructure, with exposure to JavaScript (ReactJS), C/C++, Java, Rust, and Go. You will evaluate AI-generated code for efficiency, scalability, and reliability, collaborating with researchers and

Qualifications

• 3+ years of software engineering experience.
• Proficient Python with frameworks, tooling, and production-grade software.
• Experience building full-stack applications and deploying scalable software.
• Strong communication skills for clear evaluation rationales.

Responsabilités

• Curate code examples and provide precise solutions for AI datasets.
• Evaluate AI-generated code for efficiency, scalability, and reliability.
• Collaborate with researchers and cross-functional teams on AI-driven coding solutions.
• Build Python-based verification tools to assess code quality and error patterns.
• Hypothesize steps in the software engineering cycle and evaluate model capabilities.
• Design verification mechanisms to automatically verify software engineering tasks.

Connaissances

Python

Full-Stack

Software Architecture

Communication

Description du poste

Turing Enterprises, Inc. is seeking a Software Engineering evaluator to create cutting-edge datasets for training and benchmarking large language models.

You will curate code samples, provide precise solutions, and correct errors—primarily in Python across backend services, data pipelines, and ML infrastructure, with exposure to JavaScript (ReactJS), C/C++, Java, Rust, and Go. You will evaluate AI-generated code for efficiency, scalability, and reliability, collaborating with researchers and