Backend Engineer AI Agents
Summary
Freelance backend engineers at Outlier evaluate AI agents used to train large language models: developing evaluation rubrics, investigating failures in agent traces, and testing autonomous agents against demanding workflows. Flexible remote work for those with 2+ years of backend or systems integration experience.
Apply backend engineering and modular software skills to evaluate AI agents remotely through flexible freelance work with Outlier.
Outlier collaborates with leading AI organizations to train large language models. This freelance opportunity suits engineers with at least two years of backend, AI automation, or complex systems integration experience. Contributors assess real-world agent behavior and provide precise technical feedback.
Key Responsibilities:
- Develop rubrics for evaluating agent performance
- Investigate failures across agent traces
- Test autonomous agents against demanding workflows
Requirements:
- Two or more years of relevant experience
- Ability to build production-grade modular software
- Experience handling live, non-mocked environments
- Experience with multi-turn system interactions
- Strong attention to technical detail
Bring production software expertise and careful analysis to Outlier projects training proactive, multi-step AI agents.