About the Role
The role involves developing and maintaining orchestration frameworks that manage the behavior and interactions of autonomous agents. Responsibilities include improving system reliability, scalability, and performance while collaborating closely with research and product teams.
Responsibilities
- Design and implement core orchestration logic for agent-based systems
- Build tools to monitor, debug, and manage agent workflows
- Ensure system reliability during agent execution and task delegation
- Optimize communication patterns between agents and external services
- Develop APIs and interfaces for agent coordination
- Collaborate with research teams to integrate new agent capabilities
- Create scalable infrastructure to support growing agent workloads
- Maintain documentation for orchestration components
- Troubleshoot and resolve issues in live agent environments
- Improve observability and logging across agent systems
- Support deployment and rollback processes for agent updates
- Work on fault tolerance and recovery mechanisms
- Contribute to security practices for agent interactions
- Refactor legacy orchestration components for better performance
- Participate in code reviews and system design discussions
- Assist in defining best practices for agent development
- Integrate third-party services into agent workflows
- Help shape the long-term architecture of agent systems
- Respond to operational incidents involving agent failures
- Ensure compliance with data handling standards
- Collaborate on testing strategies for agent behavior
- Evaluate new technologies for orchestration improvements
- Support onboarding of new team members to the platform
- Maintain alignment with product goals and timelines
- Contribute to incident post-mortems and preventative planning
Compensation
Competitive salary with equity and benefits
Work Arrangement
Remote with optional in-person collaboration
Team
Small, agile team focused on building foundational agent infrastructure
Why This Role Matters
As autonomous agents become more capable, coordinating their actions reliably is critical. This role directly shapes how agents interact, delegate tasks, and recover from errors, forming the backbone of scalable AI workflows.
What You’ll Build
You’ll develop the infrastructure that manages agent lifecycles, handles task routing, and ensures consistent state across distributed processes. Your work will enable more complex agent behaviors and improve system resilience.
Available for qualified candidates
