Senior Fullstack Engineer, Agent Platform
$50k - $93k • Rio de Janeiro, Brazil • Full-time
Posted 3d ago
Job Location
Rio de Janeiro, Brazil
Tech Stack
Remote Work Policy
On-site
Employment Type
Full-time
Categories
AI Agent Engineer
About the job
Commure is seeking a Senior Software Engineer to lead the platform that powers its fleet of autonomous agents. These agents are crucial for supporting teams, automating workflows, and leveraging organizational knowledge. The role involves building and maintaining the technical foundation for deploying, operating, observing, and improving these agents at scale. This position blends platform engineering with applied AI, focusing on the infrastructure, reasoning harnesses, and tools for agent development and deployment. The engineer will also ensure the existing agent fleet is secure, reliable, observable, and cost-efficient. The ideal candidate is a strong Python developer with deep Linux expertise, comfortable working across application code, operational tasks, virtual machines, Kubernetes, and cloud infrastructure.
Responsibilities
- Own the infrastructure and runtime environment for the agent fleet.
- Build, configure, deploy, and troubleshoot agents on Linux VMs.
- Develop Python services, automation, and operational tooling.
- Design and operate agent harnesses for tool use, memory, context, permissions, scheduling, and escalation.
- Create a standardized platform for agent development, testing, and deployment.
- Deploy and operate agent workloads on Linux VMs, Kubernetes, and cloud infrastructure (GCP/AWS).
- Use Bash and Linux tooling for system investigation and automation.
- Build reliable systems for agent scheduling, background execution, and concurrency.
- Develop integrations for agents to interact with internal services and APIs.
- Establish secure practices for secrets, credentials, and access control for agents.
- Build evaluation frameworks to measure agent performance (reliability, task completion, cost).
- Implement production observability for agent traces, prompts, and infrastructure.
- Create dashboards, alerting, and incident response processes for agent health.
- Diagnose failures across application code, models, tools, networks, and infrastructure.
- Improve platform efficiency and resilience as agent usage grows.
- Collaborate with product engineers to transition agent prototypes to production.
- Establish best practices for developing and operating autonomous agents.
Requirements
- Professional experience building and operating production software, infrastructure, or internal platforms.
- Strong proficiency in Python for agent development, tooling, and automation.
- Excellent familiarity with Linux environments and experience developing/deploying/debugging on VMs.
- Strong Bash and command-line skills, including scripting and diagnostics.
- Experience managing software across fleets of virtual machines (configuration, deployment, monitoring).
- Hands-on experience building and operating production systems on Google Cloud Platform or AWS.
- Experience deploying and managing Linux VMs and containerized workloads.