Staff Engineer, End-to-End Automation Platform

Antramo, Inc.; San Francisco (CA); On-site; USD 120,000 - 180,000; Full time

Job summary

Antramo, Inc. in San Francisco is building a coding agent platform for enterprise automation. You will own major parts of the system end to end, including the agents that build and repair automations, the deployment and monitoring surface, and the scalable infrastructure that runs them.

This role requires you to take ambiguous problems, make sound technical calls, and ship without a hand-off spec. Reliability is critical because downtime delays patient care in healthcare implementations.

Qualifications

• Has at least 2 years of experience shipping and operating production software.
• Has owned a production software system end to end.
• Has held on-call or equivalent responsibility for responding to production system failures.
• Has experience delivering software across frontend, backend, database, and infrastructure layers.
• Has experience working with production cloud infrastructure.
• Has experience working directly with customers or using customer feedback to shape product development.

Responsibilities

• Improve the agent system that creates and repairs automations through browser automation primitives.
• Scale the worker orchestration, job queues, and real-time coordination toward millions of daily runs.
• Build the APIs, SDKs, and observability tooling customers use to understand why an automation failed and how to fix it.
• Ship features across the stack (frontend, backend, database, infrastructure) based on customer feedback.
• Set engineering standards and help shape how the team builds as we grow.

Skills

Production software

End-to-end ownership

Cloud infrastructure

Customer feedback

Tools

AWS

Browser automation

LLM agents

Distributed systems

Job description

Antramo, Inc. in San Francisco is building a coding agent platform for enterprise automation. You will own major parts of the system end to end, including the agents that build and repair automations, the deployment and monitoring surface, and the scalable infrastructure that runs them.

This role requires you to take ambiguous problems, make sound technical calls, and ship without a hand-off spec. Reliability is critical because downtime delays patient care in healthcare implementations.