• Architect & Build: Design and implement end-to-end GenAI applications using Python, LangChain, and LlamaIndex on Google Cloud. • Engineer for Precision: Develop advanced RAG (Retrieval-Augmented Generation) pipelines and Semantic Search systems using GCP Vector Search or Pinecone. • Optimize Models: Lead efforts in LLM and Embedding fine-tuning to improve domain-specific performance. • Agentic Ops: Build and manage agentic workflows that automate complex multi-step reasoning tasks. • Collaborate & Innovate: Work directly with customers to understand requirements, suggest novel features, and implement state-of-the-art AI techniques. • Productionize: Apply MLOps best practices to ensure models are served efficiently, monitored, and continuously improved.

• Build, test, and support Conversational AI and IVR applications • Design simple, user‑friendly voice and digital experiences • Collaborate with business, design, and technology teams • Write high‑quality code and support applications through deployment • Troubleshoot and resolve complex technical issues • Stay current on emerging technologies, including AI and cloud

• Design, architect, and deploy AI-powered systems that directly impact member experience and operational efficiency • Build and optimize LLM-driven applications using advanced prompt engineering, RAG architectures, and agentic workflows • Design scalable AI pipelines using modern orchestration frameworks (LangChain, LangSmith, LlamaIndex, etc.) • Architect multi-agent systems capable of reasoning, planning, and executing complex multi-step tasks • Implement evaluation and monitoring frameworks to measure AI performance, detect hallucinations, and ensure reliability at scale • Own cloud-native AI infrastructure for performance, scalability, cost efficiency, and security • Partner with Product and Engineering leadership to identify and execute high-impact AI initiatives • Stay at the frontier of the AI ecosystem and translate emerging capabilities into production-ready systems • Establish internal standards, tooling, and best practices for AI development across the organization

• Own AI intake and delivery across Sales and CSG: run intake, clarify business problems, define requirements and success metrics, prioritize the backlog, and drive initiatives from 0 to 1 through release and iteration. • Build and ship AI workflows end-to-end: map current-state processes, identify friction, design future-state workflows, and implement agents and automations that teams can rely on day to day. • Partner cross-functionally to unblock delivery: work day-to-day with Sales, Customer Success, Marketing Ops, Business Technology, Data Science, Finance, and Legal to align on requirements, data usage, governance, and measurable outcomes. • Build with guardrails: embed permissioning, auditability, and compliance requirements into workflows from day one. • Launch what you build: drive rollout with lightweight enablement (training assets, office hours, comms), gather feedback, and continuously improve workflows after release. • Own quality and operational rigor: create test plans, run QA, manage prompt and workflow versioning, and maintain documentation, runbooks, and release notes so delivery is safe and repeatable. • Measure impact and iterate: track adoption and performance, validate results in partnership with Ops and Analytics, and continuously improve workflows based on usage and outcomes.