Australia onlyWhat you’ll actually do
This isn’t a traditional senior engineering role. You won’t spend most of your time writing product features. You’ll spend it building the system that writes them.
Right now, your time will split roughly:
- 50% building agent workflows - requirement interpretation, code generation, review, and deployment pipelines
- 50% reviewing and improving outputs - identifying failure modes and feeding those learnings back into the system
This ratio shifts over time as the agents improve. Your job is to make that shift happen. This means you’ll:
- Design agentic workflows that take a requirement from spec to production
- Review agent output with a critical eye to catch the quality issues that automated checks miss
- Identify failure patterns and turn them into system-level improvements
- Maintain and evolve the platform (TypeScript, serverless architecture, shared codebase)
- Work closely with product to reduce the ambiguity agents struggle with
This role requires strength in two areas, equally:
- Systems thinking for agent workflows. You can design feedback loops, identify where pipelines fail, and build the scaffolding (steering files, review gates, prompt structures) that makes agents reliable.
- Engineering Taste. You look at agent-generated code and immediately know whether it’s good — not just “does it work” but “does it match the conventions, is it the simplest solution, would I approve this PR.” This requires deep experience shipping production software. You can’t judge quality you’ve never produced yourself.
What we need from you
- Strong TypeScript and React experience in production environments
- You’ve shipped real software to real users, not just prototypes, so you understand the difference between code that works and code that’s production-ready
- You can read a codebase and quickly identify its patterns, conventions, and architecture
- Comfort working in ambiguity, as you’ll help define what “good” looks like in this space
Nice to have: AWS serverless experience (CDK, Lambda, DynamoDB). Our backend is a mix of modern serverless microservices and a legacy Express/PostgreSQL monolith. Familiarity with either side means faster ramp-up.
Who this role is not for
Be honest with yourself:
- If you want to spend most of your time building features directly, this role will frustrate you. The whole point is to automate yourself out of the direct build loop.
- If you’re excited about AI but haven’t shipped production software, you won’t have the taste to judge agent output. The judgment comes from experience.
- If you prefer clearly defined roles, stable scope, and established best practices, this environment won’t be a match.
The team and company
This role is part of a team of 3–4 engineers reporting to a hands-on CTO. The entire company is going all-in on this model, not just engineering. Sales, marketing, support are all building agentic workflows for their functions. This isn’t a side experiment, it’s our operating model.
We’re guided by trust, respect, and ownership. Our values, Embrace Change, Carte Blanche, Find Wisdom in Data, and We All “Own It”, shape how we work.
- We’re fully remote, so you can work from anywhere in Australia
- 5 weeks annual leave and flexible working - we believe in balance
- Monthly “Wellness Budget” to help you stay healthy, mentally & physically
- Employee share options (ESOP) for all team members - we truly all “own it”
How to apply?
To start your application with us, submit your CV via the application form. Note that background checks are required as part of our offer process.
We welcome applications from all backgrounds, abilities, and identities. We value diversity and believe that it enhances our creativity, innovation, and overall success. Join us in creating a workplace where everyone can thrive.
Managing business expenses shouldn’t be a guessing game. Yet many SMEs still lack clear cash flow visibility and spend control. At Budgetly, we’re changing that.
We’re building an AI-first platform that simplifies expense management and helps businesses make better financial decisions, faster. The goal is simple: help you spend smarter, save time, and grow profitably.
The bet
Most companies are using AI to help engineers write code faster. We’re doing something different.
We’re building AI agents that deliver product features end-to-end. Product describes what they need. Agents generate, review, and ship. Engineers design the system that makes this reliable.
If this works, feature delivery scales with the product, not headcount.
What success looks like in 12 months
- 90% of product features ship through agent pipelines
- Product Managers move from idea to deployed code without engineering bottlenecks
- Engineers focus only on complex, high-leverage problems
- Feature output grows without growing the team
