Agent Platform Engineer (Control Plane)
Primary stack
Job description
About the Position
Agent Platform Engineer (Control Plane)
MING Labs is seeking a Senior Agent Platform Engineer to build the control plane that governs a fleet of AI agents. This role is pivotal in ensuring that the platform is secure, auditable, and cost-effective. You will be responsible for creating the foundational systems that allow us to deploy agents safely and efficiently.
Responsibilities
Skill & Tool Governance
- Build systems for registering, scoping, permissioning, and versioning skills and tools.
- Prevent capability sprawl and configuration drift.
Cost Control & Model Routing
- Implement model routing and cost controls to manage spend per agent and per task.
- Provide cost-per-outcome as a reportable unit.
Audit & Accountability
- Create an audit trail that records every agent action and decision.
- Enforce decision-authority tiers, approvals, and promotions within the platform.
Agent-Building Infrastructure
- Develop the infrastructure that takes an agent from role brief to production.
- Turn recurring patterns into durable, reusable platform capabilities.
Security & Reliability
- Enforce least privilege and credential isolation.
- Ensure the reliability of the deployment substrate.
The Harness (Forward Bet)
- Pressure-test off-the-shelf runtimes and design an in-house harness.
- Lead the transition to our own runtime when the control plane is ready.
Requirements
- Strong platform or backend engineering skills.
- A real governance and security instinct.
- Comfort designing control-plane systems.
- Evidence-first habits.
- Autonomy to ship unsupervised.
- Fluency with context and retrieval substrates.
Nice to Have
- Hands-on LLM evaluation and observability tooling.
- Experience with agent frameworks or runtimes.
- Container and fleet operations at scale.
We Offer
- Ownership of the moat: Governance and audit are critical for enterprises.
- Real autonomy: Spec-and-build role with end-to-end ownership.
- A clear forward frontier: Leading the design of our own agent harness.
- High-leverage work: Every primitive you build enhances future deployments.
- Flexible, location-open working.
About the Company
We are a small, senior team building the operating model for organizations where humans and agents share the org chart. The control plane you would build is the layer everyone needs and nobody has gotten right, and it is the layer our strategy is built on. If you want to own that, with real autonomy and a founder building alongside you, this is it.
Apply
Send the AR department your work: a link to what you've built, and a few sentences on what you'd build with us. We read everything, and reply to the ones we'd want to work with.
© MING Labs. This job description was sourced from the employer's public career page. TheJob is not the employer — we index the posting and route candidates to the source. All content rights and hiring decisions belong to the employer.