Sr. SW AI Engineer

Visa Technology and Operations LLC; Austin (TX); On-site; USD 111,000 - 172,000; Full time

Benefits offered by this job

Medical

Dental

Vision

401(k)

FSA/HSA

Life Insurance

Paid Time Off

Wellness Program

Job summary

Visa Technology and Operations LLC seeks a Sr. SW AI Engineer to join a production-grade AI-first engineering team. You will design, develop, and maintain agentic systems using multi-agent LLM workflows, ReAct loops, MCP tools, and robust RAG pipelines.

On-site in Austin, TX, you’ll collaborate across teams to deliver scalable AI services and ensure observability and reliability throughout the stack. The role emphasizes Java-based backend services (Java 21), Spring Boot, REST APIs, and modern AI

Qualifications

• 2+ years of work experience with a Bachelor’s Degree or 3+ years with a Bachelor’s Degree, or more than 2 years with an Advanced Degree.
• Experience in technologies/software systems or a directly related field (minimum two years).
• Experience 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 using software developer tools for code creation and maintenance.
• Experience developing backend services in Java (Java 17+ preferred; Java 21 a strong plus).
• Familiarity with REST API design, Spring Boot, and JPA/ORM-based data access patterns.
• Foundational understanding of LLM APIs: prompt construction, token limits, and response parsing.
• Experience building and testing enterprise-scale web services (minimum one year).
• Experience working on client-facing project or technical teams (minimum one year).
• Experience mentoring junior engineers and collaborating with cross-functional teams.
• Hands-on experience building agentic AI systems using LangGraph, LangChain, LangGraph4j, or LangChain4j, including multi-agent graph construction, node/edge definitions, conditional routing, and state schema design.
• Experience implementing the React prompting pattern (Thought Action- Observation) in production or near-production LLM application.
• Working knowledge of MCP: server registration, tool schema definition, and client-side integration.
• Experience building RAG pipelines: document chunking strategies, embedding models, vector database querying, and retrieval relevance tuning.
• Experience with prompt engineering, structured output enforcement (JSON schema), and system prompt management.
• Experience building and monitoring LLM observability.

Responsibilities

• Collaborate with stakeholders to interpret requirements and incorporate feedback into designs or fixes.
• Verify assumptions while translating business requirements and escalate issues to stakeholders.
• Participate in system design and architecture, refining code plans and design docs.
• Support project estimation and escalate risks that may cause delays.
• Develop, implement, and maintain code for products and services using best practices.
• Use debugging tools to validate assumptions and flag issues proactively.
• Participate in code reviews and manage routine pull requests.
• Create test plans and configure testing procedures across features.
• Respond to support requests during on-call rotations and deploy fixes.
• Leverage tools to create, debug, and maintain code for components.
• Invest time in training resources to improve availability, reliability, observability, and performance.
• Design, implement, and tune multi-agent LLM workflows using LangGraph, LangGraph4j, LangChain4j, LangChain, including graph compilation and conditional routing.
• Build and maintain ReAct agent loops for iterative Reason Act-Observe cycles.

Skills

LangGraph

LangChain4j

LangGraph4j

LangChain

Java 17+

Java 21

REST APIs

Spring Boot

Jenkins CI/CD

Kubernetes/OpenShift

PostgreSQL

pgvector

RAG pipelines

LLM observability

AOP

Education

Bachelor’s Degree

Advanced Degree

Tools

LangGraph

LangChain4j

LangGraph4j

LangChain

PostgreSQL

pgvector

Spring Boot

Jenkins

Kubernetes

Job description

Sr. SW AI Engineer role on Visa’s AI-first engineering team, building production-grade agentic systems powered by LLMs.

Responsibilities

• Collaborate with stakeholders to interpret requirements for project components and incorporate feedback into future designs or solution fixes.
• Verify assumptions while translating business requirements; upscale potential design issues to appropriate stakeholders.
• Participate in system design and architecture, refining code plans and contributing to design documentation.
• Support project estimation and upscale risks that may cause delays.
• Develop, implement, and maintain code for products, services, or components using coding patterns, guidelines, and best practices.
• Use debugging tools to validate assumptions and proactively flag issues before they occur.
• Participate in code reviews to ensure coding standards are followed and handle routine pull requests.
• Create test plans and configure testing procedures to identify and resolve defects across multiple features.
• Respond to support requests during on-call rotations, troubleshooting issues and deploying fixes under guidance.
• Leverage and build knowledge of software developer tools to create, debug, and maintain code for components.
• Invest time in training resources to improve product availability, reliability, efficiency, observability, and performance.
• Design, implement, and tune multi-agent LLM workflows using orchestration frameworks such as LangGraph, LangGraph4j, and LangChain4j, including declarative graph compilation, conditional routing, state persistence, and dynamic agent spawning.
• Build and maintain ReAct agent loops (iterative Reason Act- Observe cycles) where an LLM selects tools, interprets tool results, and continues until a terminal answer is produced.
• Implement Supervisor/Orchestrator agent patterns where a Lead Agent dynamically plans, spawns, and coordinates Specialist Sub-Agents using conditional graph edges and tool frameworks.
• Develop MCP (Model Context Protocol) tool servers that expose enterprise data sources as callable tools for AI agents.
• Implement and refine RAG pipelines: document ingestion and chunking (PDF/Word), embedding generation, vector storage (e.g., PostgreSQL + pgvector), and semantic similarity retrieval to ground responses in authoritative documents.
• Integrate with enterprise LLM inference gateways via REST APIs, including request shaping, prompt template management, token budget control, and graceful degradation under service unavailability.
• Design agent memory architectures: short-term per-agent isolated context stores and long-term shared knowledge repositories across workflows.
• Implement confidence scoring and uncertainty quantification for AI-generated outputs, including threshold-based routing of low-confidence results to human review.
• Build agent feedback loops by capturing human reviewer decisions and feeding structured corrections back into prompt templates and knowledge repositories.
• Write LangChain4j / LangChain tool definitions (e.g., Java @Tool-annotated methods) and wire them into ReAct agents for data transformation, external API calls, and domain processing.
• Build and maintain agentic audit trails with structured logs capturing tool calls, agent decisions, LLM prompt/response, and state transitions for traceability and explainability.
• Develop and test Spring Boot microservices (Java 21, Spring Boot 3.5.x) to host AI orchestration engines, expose REST APIs, and integrate with upstream data source systems.
• Author Helm charts and Jenkins CI/CD pipelines for containerized deployment of AI services to Kubernetes/OpenShift across multi-region on-premise data centers.
• Develop and test end-to-end and integration tests for non-deterministic AI components, including prompt regression suites, tool call mock frameworks, agent output schema validators, and determinism gates to catch silent prompt drift.

Requirements

• 2+ years of work experience with a Bachelor’s Degree or an Advanced Degree (e.g., Masters, MBA, JD, MD, PhD).
• OR 3+ years of work experience with a Bachelor’s Degree, OR more than 2 years with an Advanced Degree (e.g., Masters, MBA, JD, MD).
• OR 2+ years relevant work experience with a Bachelor’s degree, OR 5+ years relevant work experience.
• Experience in technologies/software systems or a directly related field (minimum two years).
• Experience 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 using software developer tools for code creation and maintenance.
• Experience developing backend services in Java (Java 17+ preferred; Java 21 a strong plus).
• Familiarity with REST API design, Spring Boot, and JPA/ORM-based data access patterns.
• Foundational understanding of LLM APIs: prompt construction, token limits, and response parsing.
• Experience building and testing enterprise-scale web services (minimum one year).
• Experience working on client-facing project or technical teams (minimum one year).
• Experience integrating feedback into design and solution fixes.
• Experience mentoring junior engineers and collaborating with cross-functional teams.
• Hands-on experience building agentic AI systems using LangGraph, LangChain, LangGraph4j, or LangChain4j, including multi-agent graph construction, node/edge definitions, conditional routing, and state schema design.
• Experience implementing the React prompting pattern (Thought Action- Observation) in a production or near-production LLM application.
• Working knowledge of MCP: server registration, tool schema definition (tools/list, tools/call), and client-side integration.
• Experience building RAG pipelines: document chunking strategies, embedding models, vector database querying (pgvector, Pinecone, Weaviate, or equivalent), and retrieval relevance tuning.
• Experience with prompt engineering, including structured output enforcement (JSON schema), chain-of-thought prompting, few-shot example design, and system prompt management.
• Experience building and monitoring LLM observability (token usage, latency per agent step, tool call success rates, output quality metrics).
• Experience with PostgreSQL including pgvector for embedding storage and similarity search.
• Experience deploying containerized workloads on Kubernetes or OpenShift, including Helm chart authoring, rolling deployments, and health probes.
• Experience designing audit logging for AI agent decisions with structured, queryable formats capturing inputs, reasoning traces, tool calls, and outputs.
• Familiarity with Aspect-Oriented Programming (AOP) for cross-cutting concerns in Spring Boot (agent call logging, latency measurement, security enforcement).
• Experience with CI/CD pipelines (Jenkins or equivalent) for AI/ML service deployments, including version gating and environment promotion strategies.

Technologies

• Generative AI tools (e.g., ChatGPT, Microsoft Copilot)
• Large language models (LLMs)
• LangGraph, LangGraph4j, LangChain4j, LangChain
• ReAct (Reasoning + Acting)
• Model Context Protocol (MCP)
• REST APIs
• RAG (Retrieval-Augmented Generation)
• PostgreSQL, pgvector
• JPA/ORM
• Spring Boot, Java (Java 21), Spring Boot 3.5.x
• Helm charts, Jenkins CI/CD pipelines
• Kubernetes, OpenShift
• PDF, Word
• JSON schema
• Aspect-Oriented Programming (AOP)
• Pinecone, Weaviate

Benefits

• Medical
• Dental
• Vision
• 401(k)
• FSA/HSA
• Life Insurance
• Paid Time Off
• Wellness Program

Work Details

• Location: Austin, TX (onsite)
• Salary: USD 110,700 - 171,800 per yearly
• Work hours: Varies upon the needs of the department
• Travel: 5-10% of the time
• Work setting: Office setting; sit/stand at a desk; communicate in person and by telephone; frequently operate standard office equipment (telephones and computers)

Compensation Information for US Applicants

• Estimated salary range: $110,700.00 to $171,800.00 USD per year
• May include potential sales incentive payments (if applicable)
• Position may be eligible for bonus and equity

Information for Us Applicants

• Job family: Sr. SW AI Engineer