• Design, develop, and enhance applications based on foundation models (e.g., LLMs, multimodal models) tailored to specific business needs; • Implement and experiment with generative AI techniques, including but not limited to Retrieval-Augmented Generation (RAG) and prompt engineering; • Lead the implementation of intelligent autonomous agents and multi-agent systems capable of complex decision-making, task execution, and interaction with external systems; • Use and contribute to agentic AI frameworks (e.g., LangChain, AutoGen, Semantic Kernel, Crew AI) to build robust and scalable agents; • Develop and integrate Model Context Protocol (MCP) solutions to standardize how AI applications access and use external data sources, tools, and real-time information; • Lead the development of full-stack applications that integrate generative AI models and agentic systems, ensuring seamless user experiences; • Work with front-end technologies (e.g., React, Angular, Vue.js, JavaScript, TypeScript, HTML, CSS) and back-end technologies (e.g., Python with Flask/Django/FastAPI, Node.js, Go); • Design and implement scalable RESTful APIs and microservices to expose AI functionality; • Deploy, manage, and optimize AI/ML workloads and full-stack applications on at least one major cloud platform (AWS, Azure, or GCP); • Implement LLMOps/MLOps and DevOps practices for continuous integration, continuous delivery (CI/CD), model deployment, monitoring, and lifecycle management; • Stay up to date with the latest advances in generative AI, agentic systems, foundation models, and related areas through ongoing research and experimentation; • Collaborate effectively with cross-functional teams, including product managers, data scientists, researchers, and other engineers; • Mentor junior engineers, share knowledge, and foster a culture of technical excellence.

• Enhance and expand the Agentic experiences to meet the evolving needs of the Vanta platform. • Create and maintain high-quality AI patterns • Pair and collaborate with product teams on improving workflows • Help define a playbook for iterative experimentation with engineering • Bring the latest thinking to help enable our EPD organization at large

• Design, develop, and maintain scalable serverless functions using Node.js/TypeScript • Build and integrate AI-powered systems using large language models (LLMs) • Improve model accuracy, consistency, and overall output quality • Support and extend existing PHP/Laravel services • Utilize cloud platforms, particularly AWS AI services, to build, deploy, and manage AI-powered features • Drive the adoption of PrimeVue design system to ensure a cohesive UI/UX • Participate in code reviews and uphold Definition of Done standards • Collaborate with Architecture, Product Owners, and Designers to turn complex nonprofit challenges into technical specifications and high-quality design documents • Utilize AI tools to leverage technology for better planning and development.

• Advance AI Capabilities: Contribute to early-stage development of initial-phase AI systems for retrieval, ranking, categorization, and generative AI features on unstructured healthcare data. • Outcome-Driven Engineering: Deliver outcomes through software and models, ensuring projects are aligned with business objectives. • AI System Design: Work backwards from extremely complex business problems to collaborate on the design of AI components and abstractions that solve intricate problems in a maintainable and logical way. • Bring Rigor to Science Decisions: Be accountable for scientific decisions to deliver outcomes. • Mentorship and Best Practices: Provide mentorship and promote best practices in data and AI while cultivating a collaborative and inclusive team culture. • Team Growth: Contribute to hiring efforts and help identify top AI talent.