Software Engineer - Sr. Consultant level (Java & Python, GenAI, Cloud; 11-15 years' experience)

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

Job Summary:

Software Development Engineers are expert problem-solvers and builders who design, implement, and improve software applications and systems. In this role, engineers spend approximately 60–75% of their time coding, working hands-on with code, data, and modern tools (including AI-assisted development, cloud services, and automation frameworks) to deliver secure, scalable, and high-quality technology solutions that drive business outcomes in the fintech sector. They collaborate with cross-functional teams – product managers, designers, data scientists, QA, operations, and compliance – to translate business requirements into robust technical solutions, all while adhering to best practices, security standards, and regulatory requirements.

As the technical lead of the Visa Assist AI platform, you will be a hands-on, technically deep, and influential engineer who owns the technical vision and delivery of a multi-agent AI architecture (Visa Assist) serving Visa’s client-facing channels — Chat, Email, and Portal. This is a coding-intensive leadership role where you will architect, implement, and ship critical platform components while mentoring engineers, standardizing engineering practices, and aligning with stakeholders to shape the strategic roadmap for Visa’s AI-powered client services.

Key Responsibilities:

• Collaborate with business stakeholders and leadership to interpret and translate requirements across the full VisaAssist portfolio — spanning inbound channels (Chat, Email, Portal), agent worker routing logic, and platform evolution roadmaps — incorporating feedback into technical architecture decisions and working code.
• Translate business requirements into strategic roadmaps and tactical solutions — including routing logic adjustments, guardrail tuning, knowledge base curation, and CRM/billing workflow improvements — while escalating potential design issues and downstream dependencies to appropriate stakeholders.
• Lead system design and architecture, personally architecting and building core infrastructure components: intent classification models, agent routing logic, MCP protocol adapters, and resilience patterns across the distributed multi-agent system.
• Drive program delivery across the full VisaAssist portfolio — intent classification & routing accuracy improvements, agent worker ecosystem (MsgProcessing, CrmDynamics, InvoiceInvestigator, ClientProfile, Transaction Management), MCP protocol adoption and expansion across external services (CRM, Invoice, CAD CP servers), and platform reliability.
• Write production code daily (60%+ of time), personally implementing the most complex features across the full stack — FastAPI endpoints, LangChain agent orchestration, Pydantic v2 schemas, async NATS handlers, and Docker/Kubernetes configurations.
• Establish and lead engineering standards by implementing reference patterns for the Python / FastAPI / LangChain / Pydantic v2 stack, building shared library modules, and coding MCP server integration adapters (OAuth2 + SSE, mTLS + API Key, REST) that the team adopts as platform-wide standards.
• Implement LangChain agent patterns including multi-hop MCP and dynamic schema composition; prototype emerging technologies (agentic AI frameworks, MCP protocol evolution, RAG advancements) and recommend technical direction based on hands-on evaluation.
• Apply advanced debugging techniques to resolve the hardest production issues spanning multiple microservices, NATS messaging, and external service integrations, proactively flagging and addressing systemic risks.
• Design and implement observability strategies using OpenTelemetry, Prometheus, and LangSmith across the full request lifecycle (inbound channel → intent worker → NATS → agent worker → external service), with comprehensive distributed tracing and SLA target definitions for each agent worker and exter…