Autonomous Agent Runtime Engineer

NinjaTech AI; Sydney; Presencial; AUD 140.000 - 190.000; Jornada completa

Descripción de la vacante

NinjaTech AI in Sydney is seeking a Core Runtime engineer to own the agent harness that turns our LLMs into reliable, autonomous software.

You will design the run loop, orchestration, and monitoring to keep agents safe across thousands of tool calls, with a strong emphasis on scalability, observability, and fault tolerance.

Join a hands-on, research-driven team building the substrate for the next generation of autonomous AI agents.

Formación

• Master's or Bachelor's degree in Computer Science or equivalent practical experience.
• 4+ years building production backend or systems software in Python.
• Strong grasp of concurrency, process supervision, and fault-tolerant design.
• Experience with LLM APIs and agent patterns (tool calling, function calling, streaming).
• Track record of shipping and operating reliable services at scale.

Responsabilidades

• Research, design, and build the core run loop and orchestration that power autonomous agents.
• Define how agents manage context, recover from errors, and hand off work cleanly.
• Build rapid prototypes and proofs of concepts to turn harness ideas into shipped product capabilities.
• Stay up-to-date with agent architectures from research and industry, and fold the best ideas into our runtime.
• Design self-healing mechanisms so agents degrade gracefully instead of failing hard.
• Collaborate with cross-functional teams including applied science, product, and integrations.

Conocimientos

Python backend

Concurrency

Fault-tolerant design

LLM APIs

Agent patterns

Educación

Master's or Bachelor's in Computer Science or equivalent

Herramientas

Containerization

Sandboxing

Observability tooling

Descripción del empleo

NinjaTech AI in Sydney is seeking a Core Runtime engineer to own the agent harness that turns our LLMs into reliable, autonomous software.

You will design the run loop, orchestration, and monitoring to keep agents safe across thousands of tool calls, with a strong emphasis on scalability, observability, and fault tolerance.

Join a hands-on, research-driven team building the substrate for the next generation of autonomous AI agents.