10 days ago
Rio de Janeiro, BrazilSenior
Base Salary
$50k - $93k/yr
Responsibilities
- Own the infrastructure and runtime environment for Commure’s OpenClaw agent fleet.
- Build, configure, deploy, troubleshoot, and operate agents across Linux-based virtual machines, Kubernetes, and cloud infrastructure.
- Develop Python services, automation, operational tooling, integrations, and agent harnesses supporting tools, memory, context, permissions, scheduling, retries, and human escalation.
- Create a standardized platform for engineers to develop, test, deploy, and update agents safely.
- Build reliable systems for scheduling, background execution, queues, concurrency, and long-running tasks.
- Develop integrations with internal services, databases, APIs, communication platforms, and operational tools.
- Establish secure handling of secrets, credentials, identity, permissions, and access control for autonomous agents.
- Build agent evaluation frameworks and production observability for traces, prompts, tool calls, failures, latency, cost, and resource consumption.
- Create dashboards, alerting, and incident-response processes for agent and platform health.
- Diagnose failures across application code, model behavior, tools, networks, containers, virtual machines, and cloud infrastructure.
- Improve platform efficiency, resilience, reliability, repeatability, and security as agent usage grows.
- Partner with product engineers and internal teams to turn agent prototypes into dependable production systems and establish operating best practices.
Requirements
- Professional experience building and operating production software, infrastructure, or internal platforms.
- Strong proficiency in Python as the primary language for agent development, platform tooling, integrations, and automation.
- Excellent Linux fundamentals and hands-on experience developing, deploying, and debugging software on virtual machines.
- Strong Bash and command-line skills, including shell scripting, process management, networking diagnostics, filesystem operations, package management, and log investigation.
- Experience managing software across fleets of virtual machines, including configuration, deployment, monitoring, access management, and failure recovery.
- Strong hands-on production experience with Google Cloud Platform or Amazon Web Services, including compute, networking, storage, identity and access management, and observability.
- Experience deploying and managing Linux virtual machines and containerized workloads in cloud environments.
- Hands-on experience with Kubernetes, Docker, and containerized production workloads.
- Experience building infrastructure, deployment systems, internal developer platforms, or distributed application runtimes.
- Experience with infrastructure as code, configuration management, secrets management, and automated deployments.
- Hands-on experience building with large language models, autonomous agents, or agent harnesses.
- Understanding of tool calling, memory, context management, planning, retries, evaluations, permissions, and human-in-the-loop execution.
- Experience monitoring and debugging distributed systems using logs, metrics, traces, dashboards, and alerts.
- Strong understanding of production reliability, including failure recovery, idempotency, rate limiting, concurrency management, and incident response.
- Ability to balance experimentation with production security and reliability, plus strong ownership and communication skills.
- Preferred experience includes operating OpenClaw or other open-source agent frameworks, autonomous-agent fleets, multi-tenant platforms, agent evaluation and tracing, browser or computer-use agents, model gateways, prompt versioning, token accounting, LLM cost optimization, sensitive-data security, Swift, Apple client applications, healthcare, revenue cycle management, or regulated industries.
Tech Stack
Categories
About Commure
Commure builds an AI-native healthcare platform for providers and health systems, spanning ambient clinical documentation, provider copilots, coding, and revenue cycle automation, integrated with 60+ EHRs. It sells enterprise software and services to hospitals and care organizations to streamline clinical and administrative workflows. The privately held company is headquartered in Mountain View, California, and reports adoption by 500,000+ clinicians across 500+ organizations, with billions in claims processed annually.