AI Engineer (Full Stack)

Ingrity Pty; Sydney; Hybrid; AUD 165,000 - 248,000; Full time

Job summary

Ingrity Pty is seeking an AI Engineer (Full Stack) to build production‑ready AI apps end‑to‑end, combining strong software engineering with practical LLM experience. You’ll deploy across enterprise environments, optimize prompts and workflows, and partner with business stakeholders to turn AI use cases into working products.

The role focuses on end‑to‑end development, integration with data and APIs, and delivering scalable, secure solutions in a hybrid Sydney setting.

Qualifications

• 8–10 years software engineering experience.
• 2+ years AI/LLM hands-on engineering.
• Production experience with Generative AI solutions.
• Strong Python development skills.
• Front-end experience with React/TypeScript.
• Experience with LLM platforms (Azure OpenAI / OpenAI).
• Experience with LangChain, LangGraph, LlamaIndex or Semantic Kernel.
• Experience with RAG and vector search technologies.
• Knowledge of AWS/Azure, APIs, containers and CI/CD.
• Excellent communication with technical and business stakeholders.

Responsibilities

• Design, build and deploy full stack AI applications with APIs and UIs.
• Develop LLM solutions using RAG pipelines and AI agents.
• Integrate AI with enterprise data, APIs and systems.
• Refine prompts, tool calling and AI workflows.
• Take AI projects from POC to production with guardrails and cost control.
• Collaborate with product owners and stakeholders to deliver usable AI solutions.
• Ensure security, privacy and responsible AI across deployments.

Skills

Full stack development

Python

React/TypeScript

LLM engineering

Azure OpenAI / OpenAI

LangChain / LangGraph

RAG

Vector search

APIs / CI‑CD

Communication

Tools

AWS/Azure

Containers

Cloud platforms

Job description

AI Engineer (Full Stack) – GenAI / LLM

We’re partnering with a tier‑one Australian bank that is expanding its central AI engineering capability and looking to bring on experienced AI Engineers.

This is a hands‑on engineering role for someone who can build production‑ready AI applications end to end — combining strong full stack engineering with practical experience across Generative AI, LLMs, RAG and AI agents.

You’ll join a dedicated AI squad responsible for taking AI use cases from concept through to production and deploying solutions directly across different areas of the bank.

What you’ll be doing

• Design, build and deploy full stack AI applications, including backend services, APIs and user‑facing applications.
• Build solutions using LLMs, RAG pipelines, AI agents and agentic workflows.
• Integrate AI solutions with enterprise data, APIs and existing business systems.
• Develop and optimise prompts, tool calling, retrieval strategies and AI workflows.
• Take solutions from POC through to production, including evaluation, guardrails, monitoring, performance and cost optimisation.
• Partner directly with technology product owners and business stakeholders to turn AI use cases into working products.
• Build within enterprise standards across security, privacy, risk and responsible AI.

What we’re looking for

• 8–10 years’ software engineering experience, with strong full stack development capability.
• 2+ years’ hands‑on AI / LLM engineering experience.
• Demonstrated experience taking at least one Generative AI solution into production.
• Strong development experience with Python.
• Front‑end experience with React, TypeScript or similar modern frameworks.
• Experience with LLM platforms such as Azure OpenAI, AWS Bedrock, OpenAI or Anthropic APIs.
• Hands‑on experience with frameworks such as LangChain, LangGraph, LlamaIndex or Semantic Kernel.
• Experience building RAG solutions and working with vector search technologies such as pgvector, OpenSearch, Pinecone or Azure AI Search.
• Strong understanding of AWS or Azure, APIs, containers and CI/CD.
• Strong communication skills with the ability to work directly with both technical and business stakeholders.

Nice to have

• Previous experience within banking, financial services or another regulated environment.
• Experience with LLM evaluation, AI guardrails, MLOps or LLMOps.
• Exposure to data platforms such as Databricks or Snowflake.

Contract details

• Contract: 6 months, with extension likely
• Start: October / November 2026
• Location: Sydney – hybrid working