Impress employers and recruiters.
Choose from hundreds of resume examples.
Impress employers and recruiters.
Choose from hundreds of resume examples.
Target Resume Now
About the Role
We are looking for a Core Runtime engineer to own the agent harness that turns our LLMs into reliable, autonomous software. The harness is the run loop, orchestrator, and monitor that keep an agent working safely across thousands of tool calls and hours of wall-clock time. You will work at the intersection of systems engineering and applied AI, building the substrate that every SuperNinja agent runs on.
Responsibilities
- Design and evolve the agent run loop, including 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 to detect and safely intervene with stuck, looping, or runaway agents.
- Own the provider abstraction across model backends to ensure the harness remains model-agnostic.
- Make the harness observable end-to-end with structured telemetry for debuggability in production.
- Optimize the loop for speed and cost efficiency at scale to support millions of daily user interactions.
- Research, design, and build the core run loop and orchestration powering autonomous agents.
- Define how agents manage context, recover from errors, and hand off work cleanly.
- Build rapid prototypes and proof of concepts to translate harness ideas into shipped product capabilities.
- Incorporate the best ideas from agent architectures in research and industry into our runtime.
- Design self-healing mechanisms for graceful agent degradation instead of hard failures.
- Collaborate with cross-functional teams including applied science, product, and integrations.
Requirements
- 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 agentic patterns (tool calling, function calling, streaming).
- Track record of shipping and operating reliable services at scale.
- Experience building an agent framework, workflow engine, or long-running job system.
- Ability to instrument everything with an SRE mindset.
- Capacity to reason about non-determinism in LLM outputs and design around it.
- Experience with sandboxing, containerization, or secure code execution.
- Ability to move fast on prototypes while knowing when to harden them for scale.
Skills
- Python
- Concurrency
- Process Supervision
- Fault-tolerant design
- LLM APIs
- Agentic patterns
- Tool calling
- Function calling
- Streaming
- Reliable services
- Agent framework development
- Workflow engine development
- Long-running job systems
- SRE principles
- Non-determinism reasoning
- Sandboxing
- Containerization
- Secure code execution
Location
- Silicon Valley
- Sydney
- Vancouver
Work Type
- Full-time
Experience Level
- 4+ years
Education Level
- Master's or Bachelor's in Computer Science or equivalent practical experience
About the Company
- NinjaTech AI is a generative AI startup (B2C and B2B) with headquarters in Silicon Valley and offices in Sydney and Vancouver.
- Backed by Alexa Fund and Samsung Ventures, we are building the autonomous AI agents that let anyone get real work done with generative AI.
- Our flagship product, SuperNinja, is an advanced agentic AI platform with full OS capabilities: website creation, end-to-end coding, advanced data analysis, and more.
- The three roles below build the agent harness itself - the runtime, integrations, and reliability layer that every SuperNinja agent runs on.