Sr. Software Engineer (Agentic AI / GenAI / LLM / RAG, Python)

About Us Visa is a world leader in payments technology, facilitating transactions between consumers, merchants, financial institutions and government entities across more than 200 countries and territories, dedicated to uplifting everyone, everywhere by being the best way to pay and be paid.

At Visa, you’‘ll have the opportunity to create impact at scale tackling meaningful challenges, growing your skills and seeing your contributions impact lives around the world.

Join Visa and do work that matters to you, to your community, and to the world. Progress starts with you.

Job Description

Visa Corporate IT has embarked on a major transformation journey to become an engineering-first organization where reliability, automation, customer experience, and end-user productivity are central to how we operate. As part of this transformation, Corporate Reliability Engineering is focused on shifting from reactive support to proactive, predictive, and preventative engineering practices that reduce operational toil, improve service reliability, and enable scalable support across Visas global workforce.

The Agentic Developer, Corporate Reliability Engineering will be responsible for designing, building, testing, and maintaining agentic automation solutions that improve reliability, reduce manual effort, and accelerate problem resolution across Corporate IT services. This role will develop intelligent workflows, reusable automation components, integrations, and human-in-the-loop solutions that help CRE teams predict issues, automate response, prevent recurrence, and continuously improve service outcomes.

This role is an Individual Contributor I5 / Analyst-level position for a technically strong developer who can translate operational challenges into well-engineered solutions. The successful candidate will apply software engineering practices, secure development standards, automation, telemetry, workflow orchestration, and GenAI/agentic capabilities to deliver measurable improvements in reliability and employee experience.

Visas Agentic Toolchain materials describe agentic work as more than using AI for individual tasks; it includes persistent sessions, shared context, built-in quality gates, human approval points, telemetry, reusable artifacts, and lifecycle integration from product intent through engineering execution, release, and outcomes. This role will apply those same principles to CRE use cases where automation, reliability, and operational accountability are critical.

Key Focus Areas:

The ideal candidate should be passionate about:

Agentic Workflow Development:

• Agentic Automation Design: Design, build, and maintain agentic workflows that support CRE operational outcomes, including incident reduction, automated triage, knowledge retrieval, service health analysis, and repeatable remediation patterns.
• Human-in-the-Loop Engineering: Create workflows that combine automation with clear human approval gates, decision points, auditability, and escalation paths where required.
• Reusable Agentic Components: Develop reusable prompts, scripts, workflow templates, APIs, connectors, and automation modules that can be applied across multiple CRE-supported services.
• Persistent Context and Knowledge Reuse: Build solutions that preserve operational context, decisions, outputs, and lessons learned so teams do not repeatedly start from scratch.

Software Engineering and Automation:

• Code Development: Create extensible, maintainable, and secure code for automation services, workflow components, scripts, and integrations.
• API and Systems Integration: Build integrations with approved enterprise platforms, support tools, telemetry sources, knowledge repositories, workflow systems, and GenAI/agentic platforms.
• Automation of Operational Toil: Identify repetitive manual tasks across CRE and convert them into reliable automation patterns that improve speed, consistency, and scalability.
• CI/CD and Release Practices: Contribute to automated validation, deployment readiness, and controlled release practices for agentic workflows and automation solutions.

Reliability Engineering and Operational Excellence:

• Predictive and Preventative Engineering: Develop solutions that help identify patterns, risks, and recurring issues before they become widespread incidents.
• Incident and Problem Management Enablement: Build tools and workflows that improve triage, root cause analysis, known error detection,…