Senior Software Engineer, Agent Platform

About the role

Commure is seeking a Senior Software Engineer to own the platform that powers its fleet of OpenClaw autonomous agents. The role sits at the intersection of platform engineering and applied AI, building the infrastructure, tooling, and runtime environment that enable safe, scalable deployment of LLM‑powered agents across the healthcare ecosystem.

Key responsibilities

• Design, build, and operate the runtime environment for OpenClaw agents on Linux VMs, Kubernetes, and cloud (GCP or AWS).
• Develop Python services, automation scripts, and operational tooling that govern agent reasoning, memory, tool use, scheduling, retries, and human escalation.
• Create a standardized platform for engineers to develop, test, deploy, and update agents securely and reliably.
• Implement observability, dashboards, alerting, and incident‑response processes for agent health, performance, and cost.
• Establish secure approaches to secrets, credentials, identity, permissions, and access control for autonomous agents.
• Build evaluation frameworks to measure agent reliability, task completion, latency, and cost.
• Diagnose and resolve failures across application code, model behavior, containers, VMs, and cloud infrastructure.
• Collaborate with product and internal teams to turn prototype agents into production‑grade services.

Required profile

• Professional experience building and operating production software, infrastructure, or internal platforms.
• Strong proficiency in Python and deep familiarity with Linux environments.
• Hands‑on experience with Bash scripting, Kubernetes, Docker, and containerized workloads.
• Experience managing fleets of virtual machines or cloud resources on Google Cloud Platform or Amazon Web Services.
• Proven ability to design reliable, observable, and cost‑efficient systems for large‑scale AI workloads.

Required skills

• Python
• Linux
• Bash
• Kubernetes
• Docker
• Google Cloud Platform
• Amazon Web Services
• CI/CD pipelines
• Infrastructure as code / configuration management
• Secrets management
• Large language models (LLMs)
• Autonomous agents / OpenClaw framework