Freelance Software Engineer (Remote)

Role Overview

Freelance Software Engineer (Fully Remote) to help design and evaluate autonomous AI agents across domains like health, education, and everyday life. You will provide expert human feedback to train large language models (LLMs) and assess multi-step, architectural workflows.

Responsibilities

• AI Agent Evaluation
  • Create evaluation rubrics with clear objective pass/fail criteria
  • Debug agent traces to identify recurring failure patterns
  • Stress test agents with edge cases, including prompt injection and tool misuse
• Technical Assessment
  • Review and analyze production-grade modular software architecture
  • Evaluate multi-turn system interactions and behaviors
  • Provide high-density technical feedback to support LLM training
• Project Workflow
  • Create an account, upload a resume/ID, and complete onboarding assessment
  • Complete flexible task assignments to begin earning

Qualifications

• Experience in backend engineering, AI automation, or complex systems integration
• Proven ability to build and maintain production-grade modular software (e.g., separate services for parsing, logic, and reporting)
• Strong command of at least two major languages (e.g., Python, JavaScript, Go, or Java)
• Experience working with SQL databases
• Proven ability to build for live, non-mocked environments and handle multi-turn interactions

Nice to Have

• Experience integrating agents with live tools such as Supabase, Gmail, and other APIs
• Familiarity with persistent state and session-tracking patterns
• Experience identifying privacy leaks, authority escalation, and indirect prompt injection vulnerabilities

Compensation

• USD $30–$50 per hour, depending on experience and task complexity
• Weekly payments via supported payout platforms (e.g., PayPal or AirTM)