Senior AI Engineer: Agentic Systems for AI Factory

Matchbox; Sydney; On-site; AUD 150,000 - 210,000; Full time

Job summary

Firmus Technologies in Sydney is seeking a Senior AI Engineer (Agents & Applications) to design, build, and operate production-grade agentic systems for AI factories across the design-build-operate lifecycle. You will connect models, inference endpoints, workload recipes, and scheduler decisions into safe, explainable workflows.

You will create agentic applications handling telemetry, logs, events, and configuration data to support planning, simulation, and continuous improvement with secure,

Qualifications

• 5+ years of software engineering experience, including AI/ML applications.
• Strong Python expertise and API development experience.
• Experience with distributed systems and production workflows.
• Hands-on with self-hosted inference platforms and model routing.
• Familiarity with multi-agent architectures and safety controls.

Responsibilities

• Design, build, and operate agentic applications supporting AI-factory planning, commissioning, validation, workload onboarding, benchmark analysis, model and recipe optimisation, scheduling, operations, maintenance, incident response, and continuous improvement.
• Define reference architectures for single-agent, multi-agent, workflow-based, eventdriven, and human-in-the-loop agentic systems.
• Build orchestration workflows using LangGraph, LangChain, LlamaIndex, Microsoft AutoGen, Semantic Kernel, CrewAI, PydanticAI, Haystack, DSPy, or equivalent frameworks.
• Select architecture per use case: deterministic workflow, planner-executor, supervisor-worker, router, reflection/verifier/judge, or event-driven.

Skills

Python

FastAPI

Async programming

Agent frameworks

Kubernetes

Model routing

Observability

Time-series data

Tools

LangGraph

LangChain

LlamaIndex

Semantic Kernel

Haystack

DSPy

CrewAI

PydanticAI

Microsoft AutoGen

Job description

Firmus Technologies in Sydney is seeking a Senior AI Engineer (Agents & Applications) to design, build, and operate production-grade agentic systems for AI factories across the design-build-operate lifecycle. You will connect models, inference endpoints, workload recipes, and scheduler decisions into safe, explainable workflows.

You will create agentic applications handling telemetry, logs, events, and configuration data to support planning, simulation, and continuous improvement with secure,