Description
Visa is building a next-generation Agentic AI services that brings intelligent, autonomous agents into large-scale distributed applications across our global ecosystem. We're seeking a Sr. Consultant Software Engineer who will architect, design, and build scalable backend systems that integrate AI agents into Visa's enterprise infrastructure.
Key Responsibilities:
- Architecture & Design:
- Architect and evolve the Agentic AI Platform to support multi-agent orchestration, retrieval-augmented generation (RAG), and integration with existing Visa microservices.
- Design scalable, secure backend systems using Java (Spring Boot) and Python (FastAPI/Flask).
- Develop RESTful and gRPC APIs that connect backend services, AI agents, and React front-end applications.
- AI & GenAI Integration:
- Integrate Large Language Models (LLMs) such as GPT, Claude, Mistral, and Gemini into backend systems.
- Build and optimize RAG pipelines using vector databases (Pinecone, Weaviate, FAISS).
- Develop orchestration and agentic workflows using LangChain, LangGraph, or Autogen.
- Scalability & Reliability:
- Lead the design and implementation of distributed, fault-tolerant systems that scale horizontally.
- Implement auto-scaling, monitoring, and observability using Kubernetes, Docker, and Prometheus/Grafana.
- Drive best practices for latency reduction, cost optimization, and service reliability.
- Leadership & Execution:
- Partner with other senior engineers, ML engineers, and product leads to define and deliver the platform roadmap.
- Mentor developers, set coding standards, and lead design reviews.
- Deliver results with urgency , balancing innovation with enterprise rigor.
- Innovation & Strategy:
- Explore new frameworks, architectures, and deployment models to push the boundaries of Agentic AI in production.
- Drive continuous improvement, automation, and open-source adoption across the engineering organization.
- AI Security & Governance:
- Design secure, compliant Agentic AI systems with built-in safeguards for data privacy, prompt security, auditability, and responsible AI usage across enterprise environments.
- LLM Quality & Evaluation:
- Define evaluation metrics and testing frameworks to measure LLM and agent performance, accuracy, latency, cost, and reliability in production.
- Platform & Developer Enablement:
- Build reusable AI platform components, SDKs, and internal tooling that accelerate adoption and enable teams to safely develop, deploy, and scale Agentic AI solutions.
- Observability & Explainability:
- Implement end-to-end observability for AI workflows, including tracing, logging, and monitoring of agent decisions and tool usage across distributed systems.
- Operational Excellence:
- Lead production readiness, incident response, and post-mortems for AI services, driving continuous improvements in resilience, scalability, and deployment practices.
- Cross-Functional Technical Leadership:
- Collaborate with product, data, ML, and security teams to translate business needs into scalable AI architectures and influence platform strategy and roadmap.