Software Engineer II - Backend/Platform Agentic AI

About the role

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.

Responsibilities

• Build and operate services delivering AI-powered features to customers, ensuring correctness, performance, and reliability in a multi-tenant distributed environment
• Implement agentic workflows and LLM integrations from design specifications, including tool calling, retrieval patterns, prompt management, and streaming responses
• Own delivery end-to-end: design, development, testing, deployment, documentation, and production support
• Contribute to CI/CD pipelines, automated testing, and release processes to ensure consistent, reliable delivery
• Monitor, debug, and improve AI systems—resolving production issues, optimizing latency, and maintaining service health
• Collaborate with senior engineers and platform teams to integrate PI-specific capabilities into shared AI infrastructure
• Follow and contribute to engineering best practices for code quality, testing, observability, security, and reliability
• Ensure adherence to Mastercard standards for AI governance, Responsible AI, and data security in a regulated environment

Requirements

• Strong Java engineering background, including building and maintaining Spring Boot microservices
• Hands-on experience in applied AI/ML (LLM integration, RAG pipelines, agentic workflows, model serving, or inference services)
• Strong understanding of REST APIs, microservices architecture, and distributed systems fundamentals
• Experience with CI/CD practices, including branching, build automation, quality gates, and deployment pipelines
• Working knowledge of production operations: logging, metrics, monitoring, and incident response
• Experience with cloud platforms (AWS or Azure)

Qualifications

• Strong proficiency in Java for backend and service development
• Experience integrating AI/ML capabilities in production (LLM APIs, model serving, retrieval pipelines, or similar)
• Solid testing discipline with experience in unit and integration testing
• Proactive ownership mindset—asks thoughtful questions, learns quickly, and improves from feedback and production insights
• Motivated to grow AI engineering expertise and take on increasing technical scope over time

Skills

• Python experience for AI/ML scripting, experimentation, or tooling
• Familiarity with agentic AI frameworks (LangGraph, LangChain, or similar)
• Experience with Databricks, Snowflake, or similar cloud data platforms
• Experience with RAG patterns, vector databases, or semantic search
• Experience with Kubernetes, Docker, or container orchestration
• Familiarity with analytics platforms, data pipelines, or BI tools
• Exposure to prompt engineering and commercial LLM APIs (OpenAI, Anthropic, Azure OpenAI)
• Experience in financial services or other regulated environments

Benefits

The base salary offered may vary depending on multiple factors, including but not limited to location, job-related knowledge, skills, and experience. Mastercard benefits for full-time (and certain part-time) employees generally include:

• insurance (including medical, prescription drug, dental, vision, disability, life insurance)
• flexible spending account and health savings account
• paid leaves (including 16 weeks of new parent leave and up to 20 days of bereavement leave)
• 80 hours of Paid Sick and Safe Time, 25 days of vacation time and 5 personal days, pro-rated based on date of hire
• 10 annual paid U.S. observed holidays
• 401k with a best-in-class company match
• deferred compensation for eligible roles
• fitness reimbursement or on-site fitness facilities
• eligibility for tuition reimbursement
• and many more