AI Innovation Engineer

BizCover; Sydney; Hybrid; AUD 150,000 - 210,000; Full time

Benefits offered by this job

Hybrid work

Recognition rewards

Casual dress code

Benefits package

Career progression

Incentive program

Diversity & inclusion

Job summary

BizCover is building an AI-first engineering team in Sydney, aiming to ship agent-driven, compliant insurance tech. You will design, prove, and productionize multi-agent systems within a regulated environment, balancing speed with governance.

Join us to own specs, build reusable agent tooling, and push for secure, observable services. Hybrid work and ongoing learning opportunities are offered in a fast-growing insurance tech platform.

Qualifications

• 3+ years in software engineering with shipping of LLM-powered apps.
• Experience delivering spec-driven features with AI agents.
• Hands-on with multiple-agent workflows and failure handling.
• Solid fundamentals in Python, TypeScript/Node, API design, testing, CI/CD, and cloud (AWS).
• Experience with retrieval systems, eval harnesses, tracing, cost and latency metrics.

Responsibilities

• Build POCs quickly using LLMs, agents, and MCP.
• Write specs that guide automation, and hand tasks to AI agents under human oversight.
• Create reusable agent tooling and guardrails to ensure reliability.
• Orchestrate agents with patterns like orchestrator/worker or pipelines.
• Migrate POCs into observable, secure services with proper audit trails.

Skills

LLM-powered apps

Agentic coding

Spec-driven delivery

Agent orchestration

Python/TypeScript

AWS

RAG & evals

Security mindset

Tools

Claude Code

Kiro

Bedrock

Job description

Who are we?

We are the leading online platform for comparing and buying business insurance.

Not to toot our own horn, but we're shaking things up in the SME business insurance market! We're all about making it easy and efficient for small businesses to get the perfect coverage they need to stay protected. Say goodbye to headaches and hello to hassle-free insurance!

Location: Sydney, NSW (Hybrid)
Employment Type: Full-time, permanent
Level: Mid-level (3-5 years' experience)
Team: Technology

The role

We're building an AI-first engineering team. We want an engineer who builds with agents and builds agents: someone who comes up with ideas, proves them fast with POCs, and ships the winners to production, safely, in a regulated insurance environment. You'll work within our guardrails, and when you see a better way, you're free to propose it and build it.

What you'll do

• Build and prove: Build POCs quickly with LLMs, agents and MCP. Define success metrics up front and use evals to show quality, cost and business value before anything scales.
• Engineer spec-first: Write requirements -> design -> tasks, hand execution to AI coding agents (Claude Code, Kiro) under human review, and keep specs, steering docs and CLAUDE.md in sync with the code.
• Build reusable agent tooling: Package workflows as skills, subagents, hooks, plugins and MCP servers the whole team can reuse. Use hooks, not prompts, for rules that must always hold.
• Orchestrate agents: Pick the right pattern (orchestrator/worker, pipeline, fan-out, routing), or one agent when one will do. Handle state, retries, token budgets and human approval gates, and run agents headless in CI/CD.
• Ship and govern: Turn POCs into tested, observable services and RAG pipelines. Protect personal information, enforce permissions, keep audit trails and set agent autonomy boundaries.
• Improve the framework: Spot bottlenecks and pitch stack changes backed by evidence.

What you'll bring

• 3+ years in software engineering, including shipping LLM-powered applications.
• Agentic coding: Daily use of AI coding agents in real delivery work. You know when to use a skill vs a subagent vs a hook vs MCP.
• Spec-driven delivery: You've written specs an agent executed and reviewed its output critically.
• Agent orchestration: You've built at least one multi-step or multi-agent workflow and know how agents fail.
• Strong fundamentals: Python and TypeScript/Node, API design, testing, CI/CD and AWS (or another major cloud).
• RAG, evals and LLMOps: You've built a retrieval system and an eval harness, and instrumented tracing, cost and latency.
• Security mindset: You design against prompt injection, data leakage and excess agent permissions, and you're sceptical of complexity for its own sake.

Nice to have: our stack

You don't need experience with all of these, they're what we use today, and you'll learn them fast.

AI Coding Agents: Claude Code, OpenHands SDK
Spec-Driven Delivery: Kiro, GitHub Spec Kit, AI-DLC
Models & Agent Runtime: Claude via AWS Bedrock, Bedrock AgentCore, Strands Agents, LangGraph
Tools & Guardrails: MCP, Cedar Policies, Bedrock Guardrails, n8n
Data & RAG: Snowflake (including Cortex), dbt, Fivetran
Evals & Observability: Langfuse, LangSmith, Braintrust, OpenTelemetry, CloudWatch
Platforms: .NET 8, Next.js 15, Salesforce, Atlassian, Terraform / AWS CDK

Bonus points: published skills, Kiro Powers or MCP servers; experience in a regulated industry (APRA CPS 234/230, Privacy Act 1988, ISO 27001, SOC 2).

• Hybrid working model with flexibility to work from home 2 days and the 3 days in the office

• Exciting and rewarding team culture
• Quarterly recognition awards
• Business Casual dress code
• Rewarding Employee Incentive Program
• Employee benefits package
• Growing company with progression opportunities

We are an equal opportunity employer and we do not discriminate on the basis of race, color, religion, sex, sexual orientation, gender identity, national origin, age, disability, or any other protected status. We encourage applications from people of all backgrounds, identities, and perspectives. We are committed to creating a diverse and inclusive workplace where everyone can thrive and grow.