We are sharing a specialised consulting opportunity for experienced Software Engineers with strong backend expertise, scalable service development, debugging, automated testing, feature implementation, and codebase optimisation to contribute to advanced AI training and software-engineering evaluation projects.

Selected professionals will create realistic and technically challenging coding tasks, develop reference implementations and deterministic verifiers, and apply practical software-engineering judgement to feature development, bug fixing, refactoring, performance optimisation, and testing. No prior AI experience is required.

Key Responsibilities

Coding Task Development

- Create realistic software-engineering tasks involving feature implementation and bug fixes - Design challenges that reflect professional backend-development scenarios - Define clear technical requirements, constraints, and expected behaviour - Ensure tasks are sufficiently complex to evaluate engineering reasoning - Apply practical software-development experience throughout task creation

Backend Engineering & Feature Implementation

- Work across Java, Node.js, Go, Rust, TypeScript, Python, C++, or comparable technologies - Develop and evaluate scalable backend services and APIs - Implement complex features within established codebases - Apply sound algorithms, data structures, and computer-science fundamentals - Maintain strong standards for correctness, maintainability, and performance

Debugging, Refactoring & Performance

• Identify and resolve software defects and system bottlenecks - Diagnose unexpected behaviour across complex applications - Refactor existing code to improve structure and maintainability - Optimise implementation performance where required - Evaluate trade-offs between reliability, complexity, scalability, and efficiency

Deterministic Verification & Testing

- Develop deterministic verifiers for coding tasks - Ensure verifiers accept reasonable valid solutions and reject incorrect implementations - Design automated tests covering expected behaviour and edge cases - Diagnose flaky or unreliable test behaviour - Apply strong testing strategy and code-review judgement across assignments

Technical Evaluation & Quality Review

• Review software-engineering outputs for technical accuracy and completeness - Assess implementation quality against task specifications - Identify weak reasoning, incomplete fixes, or inappropriate engineering approaches - Provide precise technical feedback on submitted solutions - Maintain consistent quality standards across repeated evaluation workflows

Ideal Profile

- Strong professional backend software-engineering experience - Expertise in one or more of Java, Node.js, Go, Rust, TypeScript, Python, C++, or similar languages - Track record of building scalable services and APIs - Strong debugging and software-troubleshooting capabilities - Experience identifying and resolving performance bottlenecks - Proven ability to implement complex features in established applications - Experience refactoring large or evolving codebases - Strong understanding of algorithms and data structures - Solid automated-testing and code-review instincts - Experience designing test strategies or maintaining large test suites is particularly valuable - Ability to diagnose flaky tests and improve testing standards - Strong analytical and problem-solving skills - Clear technical written communication - Ability to work independently in a flexible remote environment - No prior AI-training or model-evaluation experience is required

Engagement Details

• Independent contractor engagement - Fully remote -

Expected commitment: approximately 15 hours per week

• Flexible schedule across weekdays or weekends -

Displayed compensation range: $30–$100/hour

-

Actual compensation structure is output-based, with payment made per task that meets project specifications

• Time required per task may vary depending on experience and workflow -

Minimum weekly submission requirements apply; the source does not specify the exact number of required tasks

- Selection may include an approximately 30-minute AI interview, a tentative technical assessment, and hiring-manager review - Interview, assessment, and project work must be completed without outside assistance - Roles are typically filled within approximately 48 hours - Selected contributors should be prepared to begin initial tasks within approximately 24–48 hours after onboarding - Work will involve coding-task development, feature implementation, debugging, refactoring, deterministic verification, and technical evaluation - Work must be completed without using confidential or proprietary information belonging to any employer, client, institution, organisation, or other third party

About the Platform

This opportunity is available through 24-MAG LLC. We connect experienced professionals with remote consulting opportunities across technical, evaluation, and project-based workstreams. By submitting this application, you acknowledge that your information may be processed by 24-MAG LLC for recruitment and opportunity matching in accordance with our Privacy Policy: https://www.24-mag.com/privacy-policy