Software Engineer II (Backend / Platform - Agentic AI)

About Mastercard

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.

About AI & Decision Product Enablement (AI&DPE)

AI & Decision Product Enablement (AI&DPE) is Mastercard's innovation engine for AI-driven decisioning at global scale.

We build and enhance the platforms that power real-time intelligence across Mastercard's network - enabling:

• Millisecond-latency decisioning
• Resilient, highly available global services
• Hundreds of AI models
• Hundreds of thousands of business rules
• 0 50+ market-facing products across Mastercard Services

Products that protect revenue, mitigate fraud, and empower customers worldwide

AI&DPE teams ensure Mastercard delivers industry-leading agility, intelligence, resiliency, and scalability in every product we build.

Role

Build, enhance, and run production-grade services by taking solution blueprints from Product Engineering teams and owning end-to-end delivery-from design refinement and implementation through release, monitoring, and operational excellence.

What you'll do (Key responsibilities)

• Translate product/solution blueprints into implementable technical designs and working software.
• Develop and maintain microservices and APIs that are secure, resilient, observable, and testable.
• Own the full SDLC: requirements refinement, design, implementation, code review, testing, CI/CD, deployment, and production support.
• Build agentic workflows using LLMs and frameworks (e.g., LangChain/LangGraph), including tool-use, retrieval, and orchestration patterns.
• Implement guardrails: prompt/version management, evaluation, safety checks, latency/cost controls, and fallbacks.
• Improve reliability through monitoring, logging, tracing, SLO-minded operations, incident response, and post-incident fixes.
• Collaborate with Product Engineering, Data Science, and Platform teams to integrate services into enterprise platforms and delivery pipelines.

Ways of working

• Comfortable collaborating with product and architecture partners; can clarify ambiguity and deliver iteratively.
• Communicates clearly in design docs, PRs, and operational runbooks.
• Balances speed with reliability and quality; proactive about production health.

Typical Deliverables

• Service design notes and API contracts
• Working microservices + tests + CI/CD pipelines
• Runbooks, dashboards, alerts, and production readiness artifacts
• Agentic workflow implementations (tools, routing, retrieval, evaluation)

All About You

• Must be high-energy, detail-oriented, proactive and can function under pressure in an independent environment.
• Must provide the necessary skills to have a high degree of initiative and self-motivation to drive results.
• Possesses strong communication skills -- both verbal and written - and strong relationship, collaborative skills and organizational skills.
• Willingness and ability to learn and take on challenging opportunities and to work as a member of matrix based diverse and geographically distributed project team.
• Deep knowledge of software development processes including agile processes and test driven development.
• Experience with the design and development of complex, multi-tier software solutions.

Core technical requirements (must-have)

• Strong proficiency in Python for backend/service development (APIs, async patterns, testing).
• Solid experience with microservices, REST/gRPC APIs, and event-driven integration patterns.
• Experience with Git
• Proven experience with CI/CD and modern SDLC practices: branching, build/release automation, quality gates, and environment promotion.
• Hands-on familiarity with LLMs and agentic frameworks (LangChain, LangGraph or similar), including retrieval/tool calling and workflow orchestration.
• Strong testing discipline: unit/integration tests, contract tests, and production-safe rollout patterns (canary/blue-green).
• Production operations mindset: logging/metrics/tracing, alerting, incident response, and root-cause analysis.

Nice to have

• Experience with containers and orchestration (Docker/Kubernetes).
• Familiarity with API gateways, service meshes, and secrets management.
• Experience with vector search/RAG patterns and document processing pipelines.
• Knowledge of security practices: threat modeling, OWASP, encryption, IAM, and secure SDLC.
• Exposure to fintech/payments domain or regulated environments.

Success measures (example)

• Features delivered from blueprint to production with low defect rates.
• Improved service reliability (fewer incidents, faster MTTR).
• Well-instrumented services and repeatable releases via CI/CD.
• Agentic workflows deliver measurable accuracy/efficiency improvements with safe guardrails.

Experience level (guidance)

Typically 3 - 5 years in backend/software engineering with meaningful production ownership in distributed systems.

Corporate Security Responsibility

All activities involving access to Mastercard assets, information, and networks comes with an inherent risk to the organization and, therefore, it is expected that every person working for, or on behalf of, Mastercard is responsible for information security and must:

• Abide by Mastercard's security policies and practices;
• Ensure the confidentiality and integrity of the information being accessed;
• Report any suspected information security violation or breach, and
• Complete all periodic mandatory security trainings in accordance with Mastercard's guidelines.