Software Engineer II - Backend/Platform Agentic AIMastercard is a global technology company in the payments industry. Our mission is to connect and power an inclusive, digital economy that benefits everyone, everywhere by making transactions safe, simple, smart, and accessible. Using secure data and networks, partnerships and passion, our innovations and solutions help individuals, financial institutions, governments, and businesses realize their greatest potential.
Our decency quotient, or DQ, drives our culture and everything we do inside and outside of our company. With connections across more than 210 countries and territories, we are building a sustainable world that unlocks priceless possibilities for all.The Portfolio Intelligence (PI) program within Mastercard's Business & Market Insights (B&MI) division delivers analytics products that help financial institutions understand and grow their card portfolios. We're building a first-party AI platform that brings agentic, conversational, and generative AI capabilities directly into our products; powering features like natural-language analytics, automated report summaries, and personalized dashboard experiences for thousands of customers worldwide.This is a builder role.
You will write code daily, own components end-to-end, and ship production-grade AI-enabled services within a multi-tenant, customer-facing platform. You'll work alongside senior engineers, architects, and product partners to implement agentic workflows, integrate LLM-powered capabilities into our existing Java/Spring Boot stack, and help operate AI systems in production.About the Role:Build and operate services delivering AI-powered features to customers, ensuring correctness, performance, and reliability in a multi-tenant distributed environmentImplement agentic workflows and LLM integrations from design specifications, including tool calling, retrieval patterns, prompt management, and streaming responsesOwn delivery end-to-end: design, development, testing, deployment, documentation, and production supportContribute to CI/CD pipelines, automated testing, and release processes to ensure consistent, reliable deliveryMonitor, debug, and improve AI systems—resolving production issues, optimizing latency, and maintaining service healthCollaborate with senior engineers and platform teams to integrate PI-specific capabilities into shared AI infrastructureFollow and contribute to engineering best practices for code quality, testing, observability, security, and reliabilityEnsure adherence to Mastercard standards for AI governance, Responsible AI, and data security in a regulated environmentAll About You:Experience building and shipping AI-powered features in production environmentsStrong Java engineering background, including building and maintaining Spring Boot microservicesHands-on experience in applied AI/ML (LLM integration, RAG pipelines, agentic workflows, model serving, or inference services)Familiar with production operations, including service ownership, incident response, and observabilitySolid testing discipline with experience in unit and integration testingStrong communication skills and ability to collaborate across distributed teamsProactive ownership mindset—asks thoughtful questions, learns quickly, and improves from feedback and production insightsMotivated to grow AI engineering expertise and take on increasing technical scope over timeRequired Skills to Be Considered:Strong proficiency in Java for backend and service developmentExperience integrating AI/ML capabilities in production (LLM APIs, model serving, retrieval pipelines, or similar)Strong understanding of REST APIs, microservices architecture, and distributed systems fundamentalsExperience with CI/CD practices, including branching, build automation, quality gates, and deployment pipelinesWorking knowledge of production operations: logging, metrics, monitoring, and incident responseExperience with cloud platforms (AWS or Azure)Nice-to-Have:Python experience for AI/ML scripting, experimentation, or toolingFamiliarity with agentic AI frameworks (LangGraph, LangChain, or similar)Experience with Databricks, Snowflake, or similar cloud data platformsExperience with RAG patterns, vector databases, or semantic searchExposure to prompt engineering and commercial LLM APIs (OpenAI, Anthropic, Azure OpenAI)Experience with Kubernetes, Docker, or container orchestrationFamiliarity with analytics platforms, data pipelines, or BI toolsExperience in financial services or other regulated environments