About this role
Join the DSTA CIO Office to build, operate and optimise enterprise AI platforms and services—including LLM hosting, RAG, agent orchestration and GPU-enabled infrastructure. Responsibilities include deploying and optimising models across on-premise and cloud environments, managing GPU infrastructure and enabling enterprise-wide AI service delivery through reusable APIs, SDKs and shared services.
Skills for this role
AI Platform EngineeringLLM hostingInference servicesEmbedding servicesAI agent orchestrationModel deploymentModel optimisationQuantizationvLLMBatchingGPU infrastructureGPU resource managementKubernetesVector databasesAPIsSDKsObservabilityMonitoringCapacity planningWorkload schedulingSoftware engineeringAI operationsAgentic AIMulti-agent systemsTool integrationGenerative AIAI security