AI Engineer
Summary
Build and deploy production-grade GenAI applications using LLMs, RAG, and agentic workflows integrated with Snowflake, focusing on reliability, observability, and semantic alignment.
We are looking for a mid-level to strong, hands-on AI Engineer who can build modern AI applications end to end - not research-heavy profiles, or generic data science candidates.
We need a pragmatic builder who has personally designed, deployed, and operated production-style GenAI solutions and can clearly explain their architecture, memory/state design, trade-offs, and implementation challenges.
This is a hands-on technical delivery role within our client's Data Engineering division. You will design, build, and operate enterprise-grade AI capabilities—specifically LLM-powered and retrieval-based experiences—ensuring they move beyond POC into sustained production.
What You Will Do
- LLM & GenAI Application Engineering: Build and operate enterprise LLM/GenAI solutions seamlessly integrated with Snowflake as the core data platform.
- Production RAG & Agentic Workflows: Implement robust RAG capabilities over governed enterprise data alongside agentic workflows equipped with strict guardrails, approvals, and audit trails.
- LLMOps & CI/CD: Establish automated workflows for experiment tracking, prompt versioning, evaluation gates, and CI/CD pipelines for AI products.
- Observability & Guardrails: Instrument and monitor solution quality, latency, cost, deployment drift, and hallucination risk.
- Semantic Alignment: Partner with data engineering to align LLM outputs cleanly to conformed data models, metrics, and semantic layers.
What We Are Looking For
To be successful, you must demonstrate a dual skillset of strong software engineering fundamentals and strong, hands-on GenAI execution:
- Production Delivery: Clear evidence of building, running, monitoring, and improving enterprise AI/ML/LLM data products.
- The Technical Stack: Advanced Python engineering skills (clean code, testing, packaging) combined with strong SQL and data modelling fundamentals.
- Data Platform Expertise: Hands-on experience with Snowflake (including performance and cost controls) and dbt Cloud environments.
- Modern AI Patterns: Practical implementation of tool use, orchestration, memory/state design, prompt engineering, and human-in-the-loop patterns.
- Engineering Rigour: Automated testing workflows (unit, integration, and regression) alongside secure platform design (RBAC/RLS, secrets management).
This is a rare opportunity to join a leading Australian retail health brand, commanding a high-demand skillset that will fast-track your career trajectory.