Senior Full Stack Engineer - Agent Runtime & Platform

About the Role

This full-time position based in Sydney involves responsibility for the core runtime environment and supporting platform services that underpin the entire product. The core task environment is a sandboxed container providing a filesystem, browser, tools, and time limits for agent operations.

Key Responsibilities

• Manage the agent sandbox runtime lifecycle including provisioning, isolation, task scheduling, and controlling costs at scale.
• Develop and maintain essential platform services such as identity management, secrets handling, usage metering, object storage, workflow orchestration, and the abstraction layer for tools and connectors.
• Lead the development of a comprehensive observability stack, covering instrumentation, data ingestion, and actionable dashboards for incident response.
• Enhance infrastructure reliability by addressing failure modes that impact users and ensuring the platform can support growth without bottlenecks.

Required Qualifications and Skills

• Extensive experience (over 5 years) designing, building, and sustaining backend production systems and platforms.
• In-depth expertise with AWS, especially using Cloud Development Kit (CDK), and advanced knowledge of container orchestration mechanics beyond configuration, including schedulers and isolation boundaries.
• Strong proficiency in Python development, complemented by sufficient frontend skills to independently create necessary internal tooling.
• A practical approach favoring simplicity and functionality over overly complex architectural solutions.