Build and maintain knowledge and evaluation infrastructure for long-horizon AI agents. Develop production agents for complex customer use cases, analyze agent errors, and implement quality improvements. Build reliable backend systems supporting agent execution, evaluation, and monitoring, while partnering with senior engineers on platform reliability and quality. The role may also involve platform engineering, frontend work, and distributed systems.

Owns evaluation strategy, error analysis, agent knowledge infrastructure, and backend systems for long-horizon AI agents. The role improves agent quality, reliability, execution, monitoring, and platform scalability while mentoring engineers and shaping the AI platform roadmap. Candidates need hands-on experience building AI products and agents, developing evaluations, analyzing failures, and delivering backend or platform systems.

As an AI Engineer, you will create a unified evaluation infrastructure for AI agents, ensuring reliable performance while integrating automated pipelines and feedback systems for rapid model evaluation and quality assurance.