2 weeks ago

Agent Harness Engineer - Core Runtime

NinjaTech AI

Sydney

2 weeks ago

Apply

NinjaTech AI is seeking a Core Runtime engineer to own the agent harness that powers their autonomous AI agents. The role involves designing and evolving the agent run loop, building the orchestrator, implementing monitoring, and ensuring reliability at scale. Requires 4+ years of Python backend experience and strong concurrency skills.

Core AIRemoteFull-timeMid LevelPythonConcurrency

Agent Harness Engineer - Core Runtime

Apply

Core AIRemoteFull-timeMid LevelPython

Salary

Not specified

Work Location

Sydney, New South Wales, Australia, AU

Work Model

Remote

Experience Required

4 years

Employment Type

Full-time

Experience Level

4+ years building production backend or systems software in Python

Core Qualifications

Technical (Must-have)

PythonConcurrencyProcess supervisionFault-tolerant designLLM APIsAgentic patternsTool callingFunction callingStreamingObservabilityTelemetryOrchestrationContext managementRecovery mechanismsPrototyping

Soft Skills

Engineering rigorScientific curiosityCollaborationReliability mindset

Preferred Qualifications

Technical (Nice-to-have)

SandboxingContainerizationSecure code execution

Key Responsibilities

•Design and evolve the agent run loop: context management, turn compaction, and recovery from failed or partial tool calls
•Build the orchestrator that launches, supervises, and hands off long-running background agents without losing state
•Implement the monitoring layer that detects stuck, looping, or runaway agents and intervenes safely
•Own the provider abstraction across model backends (Claude, Codex, and others) so the harness stays model-agnostic
•Make the harness observable end to end with structured telemetry, so failures are debuggable in production
•Keep the loop fast and cheap at scale while it powers millions of daily user interactions
•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 proof 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

Agent HarnessCore RuntimePythonLLMAIAutonomous AgentsBackendSystems EngineeringRemoteFull-time

Core Qualifications

Technical (Must-have)

Soft Skills

Engineering rigorScientific curiosityCollaborationReliability mindset

Key Responsibilities

•Design and evolve the agent run loop: context management, turn compaction, and recovery from failed or partial tool calls

•Build the orchestrator that launches, supervises, and hands off long-running background agents without losing state

•Implement the monitoring layer that detects stuck, looping, or runaway agents and intervenes safely

•Own the provider abstraction across model backends (Claude, Codex, and others) so the harness stays model-agnostic

•Make the harness observable end to end with structured telemetry, so failures are debuggable in production

•Keep the loop fast and cheap at scale while it powers millions of daily user interactions

•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 proof 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