This is a AI Engineer role with slade group based in Melbourne, VIC, AU slade group Role Seniority - mid level More about the AI Engineer role at slade group Overview We are seeking an experienced AI Engineer / Architect to design, build and deploy production-grade LLM solutions. You will own both architecture and implementation across curriculum, enrolment, grades and student administration systems, working directly with capability leads and operations teams, without people management responsibilities. Main Responsibilities Design LLM solution architectures, select models and define RAG strategies, balancing cost, latency and accuracy Build data pipelines for ingestion, chunking, embeddings, retrieval and generation across multiple student-facing systems Design and implement multi-step, agentic workflows with tool integrations aligned to modern MCP-compatible patterns Develop automated and manual evaluation frameworks to measure and improve LLM quality, safety and performance Configure guardrails, PII filtering and security controls to meet enterprise standards Deploy containerised solutions with monitoring and observability across hybrid cloud environments Produce clear technical documentation and handover materials for internal teams Technical Requirements ML/AI engineering with shipped, production LLM solutions Strong Python plus DevOps tooling: Docker, Terraform, CI/CD and serverless (e.g. ECS, Lambda) Hands-on experience with LLM orchestration frameworks (e.g. LangChain, LlamaIndex or similar) Proven RAG implementations using vector databases (e.g. pgvector, OpenSearch, Pinecone, FAISS) Experience with cloud AI platforms such as AWS Bedrock/SageMaker and/or Azure OpenAI/Azure ML Familiarity with evaluation frameworks (e.g. Promptfoo, Ragas) and designing custom evaluation pipelines Solid understanding of security (KMS, VPC, private endpoints, OIDC); nice to have: fine-tuning (LoRA/PEFT), retrieval re-ranking, Databricks/MLOps and enterprise compliance exposure Before we jump into the responsibilities of the role. No matter what you come in knowing, you’ll be learning new things all the time and the slade group team will be there to support your growth. Please consider applying even if you don't meet 100% of what’s outlined Key Responsibilities ️ Designing LLM solution architectures Building data pipelines ️ Configuring security controls Key Strengths ML/AI engineering Python and DevOps tooling LLM orchestration frameworks ☁️ Cloud AI platforms Evaluation frameworks Security practices Why slade group is partnering with Hatch on this role. Hatch exists to level the playing field for people as they discover a career that’s right for them. So when you apply you have the chance to show more than just your resume. A Final Note: This is a role with slade group not with Hatch.