• Build AI-powered product features integrated into real insurance workflows. • Design and optimize LLM-based interactions across customer and internal systems. • Develop prompts, reasoning flows, and structured AI outputs for production use cases. • Evaluate model performance using real-world data, feedback loops, and experiments. • Improve reliability of AI outputs through guardrails, fallback logic, and validation layers. • Work closely with backend engineers to integrate AI capabilities into APIs and workflows. • Design and implement AI-driven automation features (chat, recommendations, decision support). • Analyze user behavior and model responses to continuously improve AI performance. • Collaborate with product, design, and engineering teams to ship end-to-end AI features. • Contribute to AI system design decisions focused on usability and real-world impact.

• Lead the design and development of production AI systems powering insurance workflow automation. • Architect AI orchestration layers connecting LLMs, backend services, and business workflows. • Own end-to-end AI system design, including inference pipelines, routing, caching, and fallback strategies. • Drive engineering decisions around latency, reliability, cost, and scalability of AI services. • Lead implementation of Observability Systems (logging, monitoring, tracing, alerting). • Review and guide backend AI implementation across engineering teams. • Collaborate with product, backend, DevOps, and operations teams to ship end-to-end AI features. • Debug complex production issues across distributed AI systems and lead root-cause analysis. • Define engineering standards and best practices for AI system development. • Mentor engineers and elevate technical execution quality across teams.

• Lead the design and development of production AI systems powering insurance workflow automation. • Architect AI orchestration layers connecting LLMs, backend services, and business workflows. • Own end-to-end AI system design, including inference pipelines, routing, caching, and fallback strategies. • Drive engineering decisions around latency, reliability, cost, and scalability of AI services. • Lead implementation of Observability Systems (logging, monitoring, tracing, alerting). • Review and guide backend AI implementation across engineering teams. • Collaborate with product, backend, DevOps, and operations teams to ship end-to-end AI features. • Debug complex production issues across distributed AI systems and lead root-cause analysis. • Define engineering standards and best practices for AI system development. • Mentor engineers and elevate technical execution quality across teams.

• Architect end-to-end AI/ML solutions • Define and implement model lifecycle controls • Design secure integration patterns across AWS, Azure, Salesforce, and Azure DevOps • Establish governance aligned to RMF constraints • Define model evaluation frameworks and implement monitoring for model performance • Oversee CI/CD integration for model deployment • Lead root-cause analysis and triage automation architecture • Mentor engineers and direct technical execution