Design, build and deploy production-grade AI agent systems for enterprise clients across Australia. You will work with LLMs, RAG pipelines, vector databases and agentic frameworks to solve real business problems in healthcare, financial services, government and more.

Key Responsibilities

• Architect and implement AI agent workflows using LangChain, LangGraph and PydanticAI
• Build RAG pipelines with vector databases (Pinecone, Weaviate, pgvector) for enterprise knowledge retrieval
• Develop multi-channel AI agents (voice, chat, SMS) integrated with client systems
• Design prompt engineering strategies, evaluation frameworks and guardrails for production AI
• Deploy and monitor AI systems on AWS (Bedrock, SageMaker) and Azure OpenAI
• Collaborate directly with enterprise clients to translate business problems into AI solutions
• Contribute to DX1’s AI governance and responsible AI practices for Australian regulatory requirements

Required Qualifications and Experience

• 3+ years in software engineering with at least 1 year focused on LLM/AI agent development
• Strong Python skills with experience in FastAPI, async patterns and production API development
• Hands-on experience with LangChain, LangGraph or similar LLM orchestration frameworks
• Understanding of RAG architectures, embedding models and vector search
• Experience with cloud platforms (AWS or Azure) and containerised deployments
• Ability to communicate technical concepts clearly to non-technical stakeholders

Bonus Points

• Experience with PydanticAI, CrewAI or AutoGen
• Familiarity with LLM observability tools (LangSmith, Helicone, Phoenix)
• Knowledge of Australian data privacy regulations and AI governance frameworks
• Background in consulting or client-facing delivery