As a Principal AI Engineer, you will define the architectural vision and governance standards for GenAI solutions at scale. You will lead the design of intelligent systems leveraging LLMs, agentic workflows, and vector-based retrieval strategies, while ensuring alignment with enterprise-level goals around security, performance, and reusability. This role operates at the intersection of deep technical expertise and cross-functional leadership.

Key Responsibilities & Skills

• Expert knowledge of Azure cloud services for designing, optimizing, and maintaining APIs
• Strong expertise in Azure SQL, including performance tuning and optimization
• Strong proficiency in API design principles and performance optimization techniques
• Solid understanding of, and experience with, enterprise-scale initiatives
• Effective collaboration with Enterprise Architects and Platform Architects
• Ability to understand business use cases and translate them into detailed technical designs
• Strong sense of accountability and ownership
• Strong proficiency in micro-services and micro front-end architecture
• Excellent problem-solving skills with a large-scale, strategic mindset
• Strong knowledge of security across application and data layers
• Strong exposure to Visual Studio and modern development environments
• Good knowledge of CI/CD processes and DevOps practices
• Demonstrated expertise in building LLM-integrated systems, embedding pipelines, and agentic workflows in production environments
• Deep understanding of prompt optimization, vector search, context management, and multi-step task orchestration
• Experience with cloud-native delivery (Azure preferred), containerized workloads, and scalable microservices
• Strong grasp of model safety, cost optimization, and observability in GenAI applications
• Build reusable components (SDKs, prompt libraries, orchestration templates) to accelerate solution delivery
• Experience integrating backend services with front-end applications; familiarity with UI functionality is a plus