Sr. SW Engineer (Python, GenAI, 4+ years' experience)

Job description

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 part of the Visa Access AI platform team, you will be an integral member of a multi-functional development team building and maintaining an AI-powered multi-agent architecture (Visa Assist) that serves Visa's client-facing channels — Chat, Email, and Portal. You will work on intent classification, intelligent routing, and specialized agent workers handling billing inquiries, case management, client profile lookups, and knowledge base retrieval — directly impacting how Visa serves its global client base. Key Responsibilities: Collaborate with stakeholders to interpret requirements for Visa Assist project components — spanning inbound channels (Chat, Email, Portal) and agent worker routing logic — and incorporate feedback into future designs or solution fixes. Translate business requirements by verifying assumptions and escalating potential design issues, including dependencies across MCP servers and external services, to appropriate stakeholders. Participate in system design and architecture, contributing design options for epics related to Intent Classifier enhancements, agent worker capabilities, and NATS messaging patterns, and contributing to design documentation. Contribute to project estimation and escalate issues that may cause delays in agile/scrum ceremonies. Develop, implement, and maintain code for microservices within the Visa Assist multi-agent architecture using Python, FastAPI, LangChain, and NATS messaging, applying coding patterns, guidelines, and best practices. Implement and optimize Agent Workers (MsgProcessing, CrmDynamics, InvoiceInvestigator, ClientProfile) using LangChain agents, MCP JSON-RPC 2.0, and RAG pipelines — optimizing for load, performance, fail-over, and recovery (SSE streaming, distributed cache, mTLS, connection pooling). Apply debugging tools and implement telemetry, distributed tracing, and monitoring using OpenTelemetry, Prometheus, and LangSmith to proactively verify assumptions and flag issues before they occur. Participate in code reviews to ensure coding standards are followed — including Pydantic validation patterns, LangChain agent design, and async FastAPI endpoints — and address routine pull requests with test automation reported in SonarQube. Create test plans and configure testing procedures to build and unit test Gateway Agent components, Agent Workers, and shared library modules, identifying and resolving defects across multiple features. Respond to support requests by tracking and managing platform uptime and ensuring adherence to incident management process SLAs within the complex multi-agent environment. Partner with cybersecurity teams on security assessments and contribute solutions for findings including API Key Auth, mTLS, OAuth2, PCI-DSS log redaction, and input guardrails (CSAM, injection, SSRF, abuse filtering). Leverage and build knowledge of software developer tools — including Docker (multi-stage builds, RHEL 8, non-root) and Kubernetes (health probes, ConfigMaps/Secrets) — to package solutions for automated deployment. Remain current in skills and improve functional knowledge within the team by training junior colleagues on the Visa Assist architecture, NATS pub/sub patterns, and MCP protocol integration. Keep peers and leads informed of progress against epics and overall scrum progress for assigned agent workers and gateway components. Visa requires at least 3 days in office, expectations of these days will be confirmed by your Hiring Manager. Qualifications Basic Qualifications: 4 or more years of work experience with a Bachelor's Degree or with an Advanced Degree Experience in technologies/software systems or a directly related field (minimum two years). Experience in developing and/or implementing web-based or mobile applications (minimum two years). Experience in system design and architecture for product components. Experience in debugging and troubleshooting software issues. Experience in code review and applying coding standards. Experience in test planning and execution for software features. Experience in responding to support requests and deploying fixes. Experience in using software developer tools for code creation and maintenance. Preferred Qualifications: Programming Languages: Strong proficiency in Python including async/await patterns, type hints (Pydantic v2), and high-performance serialization (orjson). Experience with FastAPI for building production APIs. AI/ML Frameworks: Hands-on experience with LangChain, RAG architectures, LLM API integration, prompt engineering, and agentic AI patterns. Familiarity with intent classification and NLP pipelines. Protocols & Integration: Experience with Model Context Protocol (MCP) JSON-RPC 2.0, REST APIs, Server-Sent Events (SSE), and mTLS. Understanding of agent-to-agent communication patterns. Messaging Systems: Experience with NATS, Kafka, or similar event-driven messaging systems for distributed microservice communication. API Development: Ability to design and implement robust APIs using FastAPI, including request validation (Pydantic), authentication (OAuth2, API Key, mTLS), and streaming responses. Infrastructure: Experience with Docker (multi-stage builds, security hardening), Kubernetes (container orchestration, health probes, ConfigMaps), and CI/CD pipelines. Observability: Practical experience with distributed tracing (OpenTelemetry), metrics collection (Prometheus), and application monitoring. Experience with LLM-specific observability (LangSmith) is a plus. Security: Understanding of PCI-DSS compliance, input validation/guardrails, log redaction, OAuth2 flows, mTLS certificate management, and secure coding practices. SDLC: Strong understanding of the software development lifecycle including test automation (SonarQube), deployment strategies, and release management processes. Cloud Computing: Experience developing and deploying cloud-native containerized applications. GenAI: Practical utilization of Generative AI models for code development and familiarity with LLM API integration patterns (ChatOpenAI, token management, streaming). Visa is an EEO Employer Qualified applicants will receive consideration for employment without regard to race, color, religion, sex, national origin, sexual orientation, gender identity, disability or protected veteran status. Visa will also consider for employment qualified applicants with criminal histories in a manner consistent with EEOC guidelines and applicable local law.