AI Platform engineer

Key ResponsibilitiesAI Prompt Engineering & Agent Development Design, test, and optimize advanced prompts for LLM-based applications. Develop reusable prompt libraries, templates, and orchestration workflows. Build Agentic AI solutions leveraging reasoning, tool usage, and workflow automation. Implement RAG (Retrieval-Augmented Generation) architectures and knowledge-grounded AI systems. Improve accuracy, consistency, explainability, and output quality of AI applications. Create evaluation frameworks and benchmarks for prompt effectiveness. AI Application Engineering Develop GenAI-powered enterprise applications and products. Integrate Azure OpenAI, OpenAI, Gemini, Claude, and emerging AI models into business workflows. Build APIs, microservices, and AI orchestration layers. Implement conversational AI assistants, copilots, and workflow automation systems. Leverage GitHub Copilot and AI-assisted development methodologies. Platform Engineering Build and manage scalable cloud-native AI platforms on Azure and/or AWS. Design CI/CD pipelines supporting AI workloads and model deployment. Containerize applications using Docker and Kubernetes. Develop Infrastructure-as-Code (Terraform/Bicep/CloudFormation). Ensure platform security, observability, governance, and reliability. Manage integrations across enterprise systems, data platforms, and AI services. Data & MLOps Enablement Build data pipelines supporting AI applications. Manage vector databases and semantic search infrastructure. Support model deployment, monitoring, versioning, and lifecycle management. Implement AI governance, auditability, and performance tracking. Product & Delivery Support Collaborate with architects, product managers, insurance SMEs, and engineering teams. Translate business requirements into AI-enabled solutions. Accelerate development productivity through AI-assisted engineering practices. Contribute to internal AI accelerators and FLARRE capabilities.