- Orchestrate AI coding agents in an agent-first team
- Own the architecture, evals and patterns the whole team builds on
- Hard problems in global financial data, Sydney hybrid

Our client is a fast-growing AI-native fintech. They build data infrastructure and intelligence products for financial institutions, global exchanges and data vendors, helping them modernise their data, run more efficiently and launch new data products faster. The role: Here, AI agents write most of the code. Your job is to design the system those agents work in: the skills, architecture, tests and evals that turn agent output into production software for global financial markets.

What you’ll do:

- Deliver features end to end by orchestrating teams of AI coding agents
- Build and maintain the agent skills, context, tools and MCPs the team uses
- Set the architecture principles and patterns the agent teams follow
- Build the tests and evals that let agents move rapid without breaking things, with CI as the gatekeeper
- Build AI features into products, measuring evals, tracing and cost from day one
- Work with client-facing engineers to turn client solutions into platform capability




- Help the team adopt agent-first ways of working

What you’ll bring:

- A senior full-stack background with real data depth: Python, JavaScript, SQL, data modelling and AWS
- Production software you’ve shipped that was largely built by AI agents, and the ability to explain the workflow, the guardrails and where it breaks
- Strong systems thinking and experience owning architecture
- A solid testing discipline: your tests have caught what agents got wrong
- A habit of starting things nobody asked for, and finishing them

Nice to have: Langfuse or other LLM evals and tracing, agent security near sensitive data, Iceberg, ClickHouse or Spark, React, Kubernetes, or financial markets experience. Why this role? You’ll work agent-first on a platform built for it. You’ll have real ownership, because your patterns become how the whole team builds. And you’ll solve hard problems in global financial data.

If you’re doing serious agentic engineering and want it to be your day job, apply now. You don’t know unless you ask.

📌 Agentic AI Engineer (Sydney)
🏢 luvo Talent
📍 Sydney