🛠 Tech Stack

💼 About This Role

You'll drive the development of an AI-powered SRE agent that autonomously remediates production issues. You'll work on the reasoning, learning, and integrations of the agent, as well as the underlying runtime and technical architecture. This role offers the chance to shape the product experience and solve complex challenges in a non-deterministic environment.

🎯 What You'll Do

• Design and implement agent evaluation frameworks
• Debug agent behavior, reasoning, and tool choices
• Build autonomous agents for complex multi-step tasks
• Develop self-improving systems from feedback

📋 Requirements

• Production systems experience with ML fundamentals
• Built at least one agent end-to-end
• Strong software engineering fundamentals
• Experience with high-scale distributed infrastructure (Kubernetes, Kafka, Spark)

✨ Nice to Have

• Deep SRE or platform engineering experience
• Previous startup experience