We are seeking exceptional software engineers to collaborate on a groundbreaking AI research project with one of the world’s leading labs. This role involves analyzing large, production-grade repositories to design, evaluate, and benchmark complex coding challenges that test how advanced AI models reason about architecture, logic, and performance.
Key Responsibilities- Analyze large-scale codebases and identify architectural, functional, and performance dependencies.
- Design complex, multi-step coding challenges that assess AI reasoning.
- Evaluate model-generated solutions for accuracy, coherence, and code quality.
- Cite specific functions, files, and line numbers to support your assessments.
- Produce clear, evidence-backed documentation detailing system logic and design choices.
- Apply systematic exploration , connecting logic across files before forming conclusions.
- Demonstrate architectural understanding , identifying abstractions and design trade-offs.
- Have experience using AI coding agents (Copilot, GPT-4, Claude, or Replit Agents) in your workflow.
- Write precise, structured technical documentation and communicate complex reasoning clearly.
- Competitive task-based compensation (top contributors have earned $1,000+ per sprint)
- Weekly payouts via Stripe Connect
Apply Now!
Seniority levelNot Applicable
Employment typePart-time
Job functionSoftware Development
#J-18808-Ljbffr