Overview
Join Visa's Corporate Generative AI Technologies team as a Staff Software Engineer building and scaling enterprise-grade Generative AI and agentic applications. This senior, hands-on role covers full-stack product engineering, system design, AI-enabled workflow automation, and production-grade GenAI solutions.
What you'll do
- Design, build, and scale enterprise-grade GenAI and agentic applications with maintainable, secure, scalable, reliable, and production-ready architecture.
- Own delivery of GenAI subsystems, lead design reviews, and mentor I4/I5 engineers.
- Build full-stack production-grade applications with robust API design, workflow orchestration, secure data flows, observability, and operational readiness.
- Build modern frontend experiences using React, including component-based architecture, state management, reusable UI components, accessibility, performance optimization, and integration with backend APIs and AI-enabled services.
- Design and implement scalable backend services using Python, Node.js, and/or Java, including secure APIs, asynchronous processing, background jobs, authentication, authorization, logging, error handling, and system resiliency.
- Work with PostgreSQL, Redis, vector databases, and related technologies, including schema design, indexing strategies, query optimization, transaction management, caching patterns, migrations, and data access patterns.
- Implement backend capabilities for AI-enabled and agentic workflow automation, including intent routing, agent orchestration, tool execution, API integrations, data retrieval, multi-step execution, workflow state management, human approval flows, guardrails, auditability, and enterprise system integration.
- Develop AI-native capabilities using OpenAI, Anthropic, and related LLM APIs/SDKs, including prompt orchestration, tool/function calling, structured outputs, streaming responses, model routing, and evaluation patterns.
- Apply modern LLM capabilities to make engineering decisions around model selection, context management, latency, cost, reliability, output quality, safety, and user experience.
- Design and implement retrieval-augmented generation solutions, including ingestion pipelines, ETL workflows, embeddings, vector database integration, retrieval strategies, relevance ranking, grounding, and retrieval quality evaluation.
- Build and deploy cloud-native applications using containers, DevOps practices, CI/CD pipelines, automated testing, monitoring, and operational automation.
- Work with engineering teammates and cross-functional partners to translate ambiguous requirements into proof-of-concepts and evolve them into production-quality solutions.
- Implement observability and operational excellence for GenAI applications, including end-to-end tracing, workflow telemetry, model evaluation, and monitoring.
What you'll need
- 8+ years of professional software engineering experience designing, building, and operating production-grade applications.
- Bachelor’s degree in computer science, Engineering, or related field.
- Hands-on experience developing and deploying GenAI-based enterprise solutions.
- Good understanding of integrating model capabilities into production applications.
- Hands-on experience with React and backend development using Python, Node.js, Java, or similar languages.
- Strong technical judgment and system design experience, including evaluating tradeoffs across scalability, security, reliability, maintainability, performance, cost, and delivery speed.
- Familiarity with multi-agent GenAI solutions incorporating agentic behaviors using A2A and MCP protocols.
- Experience with Redis, Postgres, vector databases, embedding models, and RAG pipelines.
- Experience with DevOps practices, CI/CD pipelines, and version control systems.
- Proven ability to lead cross-functional AI initiatives, including PoC development, stakeholder alignment, and enterprise rollout.
- Excellent communication skills with the ability to translate complex technical concepts to business stakeholders.
- Experience with Python and FastAPI.
- Experience with AWS, Azure, Docker, Kubernetes, and ECS.
- Experience with Git and CI/CD pipelines.
- Experience with Pinecone, Redis, and PostgreSQL.
- Experience with Prometheus, Grafana, audit logging, and access control.
- Experience with ReactJS, HTML, CSS, and JavaScript.
Nice to have
- Anthropic/OpenAI SDKs, MCP, and A2A is a plus.
Details
- Location: Bengaluru, India.
- At least 3 days in the office are required; expectations for these days will be confirmed by the Hiring Manager.
Read the full description and apply on the company’s own careers page.