Firmus
Senior AI Engineer, Agents & Applications
Sydney, New South Wales, Australia. Posted 2 months ago
The role
The Senior AI Engineer will design, build, and operate production-grade agentic systems for AI factories. This role involves creating agentic applications that reason over telemetry, logs, and multimodal sources to automate decision-making across the design-build-operate lifecycle.
What you will do
- Design, build, and operate agentic applications for AI-factory planning, commissioning, and maintenance.
- Define reference architectures for single-agent, multi-agent, and human-in-the-loop systems.
- Build orchestration workflows using agent frameworks and libraries.
- Develop specialist agents for benchmark analysis, workload recommendation, and diagnostic tasks.
- Develop the intelligent coordination layer for Model-to-Grid.
- Build Retrieval-Augmented Generation (RAG) pipelines.
- Design knowledge-ingestion pipelines for documentation and operational data.
- Integrate agents with Kubernetes, scheduler services, and observability platforms.
- Define tool contracts using structured input and output schemas.
- Implement agent observability, evaluation frameworks, and security controls.
Required qualifications
- 5+ years of software engineering experience
- 3+ years building AI/ML applications, distributed systems, automation platforms, data products, or production workflow systems
- Demonstrated experience delivering LLM-powered, agentic, retrieval-augmented, decision-support, or operational-automation applications into production
- Strong Python expertise
- Experience with FastAPI or comparable API frameworks
- Experience with asynchronous programming, event-driven services, distributed task execution, data pipelines, and API integrations
- Hands-on experience with one or more agent frameworks such as LangGraph, LangChain, LlamaIndex, Microsoft AutoGen, Semantic Kernel, CrewAI, PydanticAI, Haystack, or DSPy
- Ability to build custom agent orchestration including state machines and graph-based execution
- Experience with workflow and orchestration technologies such as Temporal, Dagster, Prefect, Airflow, Argo Workflows, Kubernetes Jobs, or Celery
- Strong understanding of multi-agent architectures
- Practical experience with RAG architectures
- Experience with vector databases, search platforms, or graph databases such as pgvector, OpenSearch, Elasticsearch, Milvus, Weaviate, Pinecone, Qdrant, or Neo4j
About the company
Firmus Technologies is a global leader pioneering the development and operation of efficient AI infrastructure across Asia Pacific. The company designs, builds, and operates AI Factories using a model-to-grid technology approach.