Remote Backend Engineer for AI Evaluation Tasks

24-Mag Llc; New York (NY); Hybrid; USD 83,000 - 138,000; Part time

Benefits offered by this job

Remote work

Flexible schedule

Competitive pay

Job summary

24-MAG LLC invites senior backend engineers to contribute to a high-caliber AI training and software-evaluation project. You will craft realistic coding tasks, implement deterministic verifiers, and assess submissions against robust evaluation criteria.

The role emphasizes production-grade backend systems, scalable APIs, and security-conscious design. You will work as an independent contractor, remotely, with an approximately 15 hours per week commitment and a pay range of $30–$100 per hour,

Qualifications

• Extensive backend software engineering experience.
• Strong debugging, automated testing, and performance optimization skills.
• Proven ability to design realistic coding tasks and evaluation scenarios.

Responsibilities

• Design and develop realistic backend-engineering tasks.
• Create challenging production-like scenarios for evaluation.
• Define clear technical requirements and expected behavior.
• Ensure tasks support multiple valid approaches and robust verification.
• Review code for quality, safety, and maintainability.

Skills

Backend engineering

Java

Node.js

Go

Rust

TypeScript

Python

C++

Code review

Testing

Performance

Security

Tools

Git

CI/CD

Job description

24-MAG LLC invites senior backend engineers to contribute to a high-caliber AI training and software-evaluation project. You will craft realistic coding tasks, implement deterministic verifiers, and assess submissions against robust evaluation criteria.

The role emphasizes production-grade backend systems, scalable APIs, and security-conscious design. You will work as an independent contractor, remotely, with an approximately 15 hours per week commitment and a pay range of $30–$100 per hour,