Software Engineer, Platform

About Sidekick Machines

Sidekick Machines is an AI startup that builds and runs AI agents for enterprises. Most agent projects stall on infrastructure: identity, security, integrations, approvals, monitoring and cost. We built our own platform, Sidekick, on Microsoft's agent stack to handle that infrastructure. Our engineers spend their time on the work that matters, and we stay on to run every agent we ship.

Agentic AI is new, and nobody has a decade of it. We hire people with strong fundamentals and the drive to figure things out, and we teach the rest.

The role

You'll build the Sidekick platform, the foundation every agent we deliver runs on. It's what lets our FDEs put an agent into production without rebuilding identity, security, integrations and observability each time. You'll report directly to our CTO and Head of Engineering and work closely with them on architecture.

We hire for engineering judgment, not for a specific resume. If you write clean, well-reasoned software, make good design calls, and use AI coding tools to move fast, you'll do well here.

What you'll work on

• The agent runtime: how agents load skills, call tools, run hooks, wait for human approval and pick back up.
• Identity and security for agents, built on Microsoft Entra and Agent 365.
• Distributed services on Kubernetes that run reliably at enterprise scale.
• Model access and evaluation on Microsoft Foundry.
• The tracing, evals and cost tracking our operations team depends on.

What we're looking for

• 5-10 years experience with Strong software engineering fundamentals and a proven track record of shipping production systems.
• Experience with some of: Kubernetes, distributed systems, microservices, identity and auth (OAuth, OpenID Connect), harness or developer-platform engineering.
• Good taste: simple designs, readable code, sensible trade-offs.
• Serious use of AI coding tools, and a sense of how to get good work out of them.
• Ownership of what you ship, end to end.

Bonus

• Experience with LLMs, agent frameworks or MCP.
• Azure experience.

Training

You'll learn the agent side from the team as you go.

Compensation and how to apply

• Compensation: Salary plus ESOPs
• To apply: [Confidential Information]