Software Engineer II - Cloud-Native Agent Harness (Mecatl)

Stacklok is hiring a Software Engineer II for its Mecatl team, which builds an open source, cloud-native agent harness. The role develops and maintains agent platform features across the runtime, client SDKs, and security and governance layers, while using and improving AI-assisted engineering workflows.

Responsibilities:

• Build and deliver features in the open across Mecatl, including the agent loop, tool and permission systems, session and state management, the Kubernetes runtime, and client SDKs
• Fix bugs and harden the harness for production use, improving reliability, security, and observability
• Write testable, readable code that accounts for edge cases and error handling, produce clear design docs for the work you take on, and review pull requests, including AI-assisted changes
• Understand outcomes and partner with the team anchor to break down the work. Escalate decisions to product or staff engineers as needed
• Use AI agents as a core part of your own workflow, and bring a critical eye to what they produce: review it, test it, and own it
• Find where your AI workflow breaks down on Mecatl work, experiment to fix it, and bring structured findings back so the team gets faster and better, not just busier
• Apply security judgment to AI-assisted development, including permissions, secrets handling, untrusted content, and the limits of what an agent should be trusted to do

Requirements:

• Proficiency in Go, writing clean, testable code that accounts for edge cases and error handling, plus clear design docs and thoughtful code reviews
• Demonstrated ability to deliver features independently across a backend or platform codebase, from implementation through testing and into a release
• Working knowledge of distributed systems and cloud-native infrastructure, such as Kubernetes, containers, and service APIs (gRPC or HTTP)
• A personal AI-assisted development workflow you can walk through, with a clear sense of where it helps, where it breaks, and its risks, such as prompt injection and excessive agent permissions
• Interest in agent infrastructure, such as agent loops, tool use, MCP, model providers, or evaluation
• AI-first mindset: builds AI into the development workflow to accelerate delivery, improve the quality of what ships, and rethink how problems get solved
• Communication: excellent written and verbal communication, able to explain complex technical ideas clearly to technical and non-technical audiences
• Startup mentality and intrinsic motivation: self-directed and hands-on, thrives in fast-moving, ambiguous environments, and drives clarity through action
• Experience with durable state, concurrency, or streaming is a plus
• Prior experience building on or contributing to an AI platform or open source project is a plus
• Ideally, a product engineering mindset: curious about users and their problems, comfortable questioning requirements, and motivated by shipping something people use