Production AI Engineer — Full-Stack & LLM Orchestration

Latitude IT; Sydney; On-site; AUD 120,000 - 180,000; Full time

Job summary

Latitude IT seeks a software engineer to apply AI in production across a fast-growing Australian marketplace. You’ll own end-to-end delivery of production-grade AI agents and scalable services, shaping architecture and reusable patterns.

You’ll work with a hands-on CTO, integrate LLMs and external APIs, implement guardrails, testing and observability, and relentlessly improve reliability and performance across customer interactions and internal workflows.

Qualifications

• Proven track record shipping production AI apps.
• Experience designing scalable architectures for AI-driven products.
• Ability to communicate across technical and non-technical audiences.
• Ownership from discovery through production and iteration.

Responsibilities

• Designing, building and deploying production AI agents across customer interactions, automation and internal workflows
• Building scalable full-stack applications in TypeScript, Node.js, React and AWS, integrating LLMs and external APIs
• Creating reusable components and guardrails to speed AI delivery across the business
• Owning technical design across architecture, integrations, reliability, security and performance
• Collaborating with product, engineering and business teams to identify commercial AI value
• Setting testing, monitoring and maintenance standards for AI in production

Skills

Ownership

Ambiguity tolerance

Communication

Cross-team collaboration

Customer impact awareness

Tools

TypeScript

Node.js

React

AWS

LLM orchestration

Multi-agent systems

Guardrails

Observability

Tool calling

Job description

Latitude IT seeks a software engineer to apply AI in production across a fast-growing Australian marketplace. You’ll own end-to-end delivery of production-grade AI agents and scalable services, shaping architecture and reusable patterns.

You’ll work with a hands-on CTO, integrate LLMs and external APIs, implement guardrails, testing and observability, and relentlessly improve reliability and performance across customer interactions and internal workflows.