AI Principle Architect

Our Purpose Mastercard powers economies and empowers people in 200+ countries and territories worldwide. Together with our customers, we’re helping build a sustainable economy where everyone can prosper. We support a wide range of digital payments choices, making transactions secure, simple, smart and accessible. Our technology and innovation, partnerships and networks combine to deliver a unique set of products and services that help people, businesses and governments realize their greatest potential. Title and Summary AI Principle Architect Mastercard's Business & Market Insights (B&MI) group empowers organizations to achieve growth and innovation goals by delivering unparalleled data-driven intelligence and cutting-edge AI solutions. By harnessing proprietary data, frontier generative AI, and global expertise, B&MI helps businesses make smarter, faster, and more impactful decisions. We transform complex, multi-modal data into agentic systems and generative applications that drive measurable business outcomes and sustained competitive advantage. We're looking for a Principal Architect, Generative AI & ML Engineering, for the Operational Intelligence Program within B&MI. As a principal-level technical leader, you'll define the architecture vision and technical strategy for our agentic AI platform. On this platform, agents make extensive tool calls into enterprise services and APIs and must run securely, reliably, and at scale. You'll set the standards teams build on across tool calling, multi-agent orchestration, self-correcting agents, memory, retrieval, and LLMOps. You'll also make the key decisions on models, platforms, and trade-offs. Working closely with engineering, product, security, and business leaders, you'll shape the long-term direction of Gen AI across B&MI and mentor architects and senior engineers. You'll also stay hands-on with prototypes that de-risk big bets. The hardest problems in enterprise Gen AI are reliability, integration, security, and scale. If you've solved them as a backend or distributed systems architect and have started applying that experience to LLM systems, we'd love to hear from you. Roles & Responsibilities • Own the architecture and technical roadmap for the Operational Intelligence Gen AI platform, defining reference architectures and standards that teams across the program can reuse and scale. • Architect the enterprise tool-calling layer, setting standards for how internal services, data platforms, and external APIs are exposed to agents as tools. This covers schemas, contracts, versioning, access control, and resilient execution (parallel and chained calls, retries, timeouts, idempotency, circuit breakers, and fallbacks). • Set the architecture for multi-agent and skills-based agent systems (e.g., LangGraph, CrewAI, AutoGen), including when to use agents versus deterministic workflows and how agents coordinate, delegate, and share context. • Design self-correcting agent patterns: tool critics and verifiers that check tool selection, arguments, and results, plus reflection and plan-and-execute loops that catch errors before agents act or respond. • Architect agent memory and state for long-running, multi-step sessions, including short- and long-term memory (e.g., Mem0, Zep, LangGraph memory), session persistence, and memory scoping and retention. • Define retrieval architecture for grounded reasoning, including Self-RAG, Corrective RAG (CRAG), adaptive retrieval, and Graph-RAG, built on vector databases (e.g., Pinecone, pgvector, OpenSearch) and knowledge graphs (e.g., Neo4j, AWS Neptune). • Design the inference and orchestration layer for high throughput, covering async processing, streaming, caching, rate limiting, and model routing across OpenAI, Anthropic, Gemini, and open-source