Software Engineer II (Cloud-Native Agent Harness)

Quick Facts

• Role: Software Engineer II (Cloud-Native Agent Harness)
• Focus: Building Mecatl, a cloud-native harness for running production AI agents on Kubernetes
• Work style: Hands-on engineering with independence; AI-first development practices

Description

Build the platform that AI agents run on by delivering features across the Mecatl engine, Kubernetes-native runtime, and client interfaces. You’ll also strengthen the permission and governance layers that make agent behavior safe and trustworthy, while improving reliability, security, and observability. The team uses AI agents in its own development lifecycle and expects you to run experiments and feed learnings back into how the team works.

Responsibilities

• Build and deliver features in the open across Mecatl (agent loop, tool and permission systems, session and state management, Kubernetes runtime, client SDKs)
• Fix bugs and harden the harness for production use to improve reliability, security, and observability
• Write readable, testable code with strong edge-case and error handling; produce design docs; review pull requests (including AI-assisted changes)
• Understand outcomes, partner with the team, and escalate decisions when needed
• Use AI agents in your workflow; apply a critical eye by reviewing, testing, and owning what the workflow produces
• Identify where your AI workflow breaks down on Mecatl work, experiment to fix it, and report structured learnings
• Apply security judgment to AI-assisted development (permissions, secrets handling, untrusted content, and trust boundaries)

Requirements

• Proficiency in Go, writing clean, testable code that accounts for edge cases and error handling, plus ability to write clear design docs and perform thoughtful code reviews
• Ability to deliver features independently across a backend/platform codebase (implementation through testing and release)
• Working knowledge of distributed systems and cloud-native infrastructure (Kubernetes, containers, service APIs such as gRPC or HTTP)
• Plus: experience with durable state, concurrency, or streaming
• Ability to use and evaluate an AI-assisted development workflow, including awareness of risks (e.g., prompt injection, excessive agent permissions)
• Interest in agent infrastructure (agent loops, tool use, MCP, model providers, or evaluation); prior AI platform/open source contributions are a plus
• Product engineering mindset and excellent written/verbal communication

Benefits

• Anticipated base salary range: $157,500 - $192,500, plus equity
• Comprehensive medical, dental, and vision coverage
• Flexible hybrid or remote work environment
• Flexible PTO, paid holidays, and paid parental leave; team offsites