Sr. SW Engineer - Agentic Developer (Java/Python, 3-5 yrs of experience)

Visa; Bengaluru; On-site; INR 3,000,000 - 6,500,000; Full time

Job summary

Visa in Bengaluru is seeking an Agentic Developer to design, build, test, and maintain agentic automation that enhances reliability, reduces manual work, and accelerates problem resolution across Corporate IT services.

You will collaborate with CRE engineers, IT security, QA, and product teams to deliver production-ready automation while applying secure development practices and measuring business impact.

Qualifications

• Bachelor’s degree in Information Technology, Computer Science, Engineering or related field.
• 5+ years in software development, automation engineering, AI/ML, or reliability roles.
• Proven ability to create maintainable code, scripts and workflow-based solutions.
• Proficiency in Python, PowerShell, Bash, JS/TS, Java, or similar, with AI/orchestration exposure.
• Experience with APIs, version control, testing, debugging, and documentation.
• Familiarity with LLMs, RAG, agent orchestration concepts, and secure development practices.

Responsibilities

• Design, develop, test, and maintain agentic workflows and automation solutions for CRE.
• Translate CRE pain points into technical requirements, designs, and plans.
• Build maintainable code, scripts, APIs, connectors, and reusable automation components.
• Integrate automation with enterprise systems, telemetry, and knowledge repositories.
• Develop automated tests, quality gates, and release readiness reporting.
• Analyze incidents and telemetry to identify automation opportunities and improvements.

Skills

Python

PowerShell

Bash

JavaScript/TypeScript

AI/ML engineering

Agentic systems

APIs

Source control

LLMs

Secure development

Communication

Education

Bachelor’s degree in Information Technology, Computer Science, Engineering

Tools

LangChain

LangGraph

CrewAI

AutoGen

Semantic Kernel

GitHub

Azure DevOps

ServiceNow

Jira

Copilot Studio

Job description

Job Description

Visa Corporate IT is undergoing a transformation to become an engineering-first organization focused on reliability, automation, customer experience, and end-user productivity. As part of this shift, Corporate Reliability Engineering (CRE) is moving from reactive support to proactive, predictive, and preventative engineering practices. The Agentic Developer will design, build, test, and maintain agentic automation solutions that improve reliability, reduce manual effort, and accelerate problem resolution across Corporate IT services.

Key Focus Areas

• Design, build, and maintain agentic workflows that support CRE operational outcomes such as incident reduction, automated triage, knowledge retrieval, service health analysis, and repeatable remediation patterns.
• Create human‑in‑the‑loop workflows with clear approval gates, decision points, auditability, and escalation paths.
• Develop reusable prompts, scripts, workflow templates, APIs, connectors, and automation modules applicable across multiple CRE‑supported services.
• Build solutions that preserve operational context, decisions, outputs, and lessons learned to avoid repeat starting from scratch.

Software Engineering and Automation

• Write extensible, maintainable, and secure code for automation services, scripts, and integrations.
• Integrate with approved enterprise platforms, support tools, telemetry sources, knowledge repositories, workflow systems, and GenAI/agentic platforms.
• Identify repetitive manual tasks across CRE and convert them into reliable automation patterns.
• Contribute to automated validation, deployment readiness, and controlled release practices for agentic workflows.

Reliability Engineering and Operational Excellence

• Develop solutions that identify patterns, risks, and recurring issues before they become widespread incidents.
• Create tools and workflows that improve triage, root‑cause analysis, known‑error detection, remediation recommendations, and post‑incident learning.
• Use operational data, logs, metrics, ticket trends, and user‑experience signals to inform automation opportunities and measure effectiveness.
• Partner with CRE teams to identify reliability gaps, automation opportunities, and process improvements that reduce incidents, escalations, and manual support effort.

Testing, Quality Gates, and Controls

• Build automated checks and tests that validate workflow behavior, integration accuracy, data quality, and expected outcomes before release.
• Implement quality gates that prevent incomplete, unsafe, or low‑confidence automation from progressing without review.
• Create repeatable tests to ensure updates to prompts, workflows, scripts, integrations, and logic do not break existing capabilities.
• Produce clear reporting that demonstrates test coverage, pass/fail results, risk areas, and readiness for production use.

Reporting, Analytics, and Business Impact

• Partner with analytics and operations teams to develop dashboards that show automation adoption, effectiveness, reliability impact, time saved, and recurring issue reduction.
• Define success metrics for each agentic solution, including reliability improvement, reduced manual effort, improved response time, improved knowledge reuse, or reduced recurrence.
• Analyze recurring incidents, service degradation patterns, ticket drivers, and operational bottlenecks to identify high‑value automation candidates.
• Translate technical outcomes into concise business impact statements for CRE, CIT, and leadership stakeholders.

Collaboration and Process Improvement

• Work closely with CRE engineers, Client Engineering, Microsoft Backend, Workstation Vulnerability Remediation, QA, Service Desk, Onsite Support, Information Security, Architecture, and Product teams.
• Communicate technical concepts, solution design, risks, and results clearly to both technical and non‑technical audiences.
• Maintain documentation, runbooks, design notes, workflow logic, decision records, and support guides for all agentic solutions.
• Promote engineering‑first practices within CRE by encouraging automation, reusable design, code quality, peer review, testing discipline, and continuous learning.

Responsibilities

• Design, develop, test, and maintain agentic workflows and automation solutions for Corporate Reliability Engineering.
• Translate CRE operational pain points into technical requirements, workflow designs, implementation plans, and measurable outcomes.
• Build maintainable code, scripts, APIs, connectors, and reusable automation components.
• Integrate automation solutions with approved enterprise systems, telemetry sources, knowledge repositories, and operational workflows.
• Apply secure development practices, coding standards, code reviews, testing, and documentation.
• Develop automated tests, validation logic, quality gates, and release readiness reporting for agentic workflows.
• Analyze incident, ticket, telemetry, and service‑health data to identify automation and reliability improvement opportunities.
• Partner with CRE and cross‑functional teams to reduce manual toil, improve reliability, and prevent recurring issues.
• Document workflows, support models, runbooks, and operational handoff materials.
• Continuously evaluate new tools, technologies, and agentic patterns that can improve CRE effectiveness.

Success Measures

• Deliver reliable agentic workflows and automation solutions that reduce manual effort and improve CRE operational outcomes.
• Successfully design, develop, and deploy production‑ready AI agents that automate business workflows while meeting security, compliance, and operational requirements.
• Increase automation coverage across recurring CRE support scenarios.
• Reduce repetitive ticket handling, manual triage, and repeated troubleshooting effort.
• Improve speed, consistency, and quality of incident/problem analysis.
• Build reusable automation components that can scale across multiple services and teams.
• Produce clear documentation, test evidence, quality metrics, and business impact reporting.
• Demonstrate responsible use of GenAI and agentic automation through human approval points, quality gates, auditability, and secure engineering practices.

Visa requires at least 3 days in the office; the specific days will be confirmed by the Hiring Manager.

Basic Qualifications

• Bachelor’s degree in Information Technology, Computer Science, Engineering, or a related field, or equivalent practical experience.
• 5+ years of experience in software development, automation engineering, AI/ML engineering, agentic systems development, reliability engineering, platform engineering, endpoint engineering, or related technical roles.
• Demonstrated experience developing maintainable code, scripts, automations, integrations, or workflow‑based solutions and agent‑based applications.
• Proficiency in one or more programming or scripting languages such as Python, PowerShell, Bash, JavaScript/TypeScript, Java, or similar, with preference for experience building AI, LLM, API, and agent orchestration solutions.
• Experience with APIs, source control, testing, debugging, and technical documentation.
• Familiarity with Large Language Models (LLMs), prompt engineering, Retrieval‑Augmented Generation (RAG), agent frameworks, or AI orchestration concepts.
• Understanding of secure development practices, code review, and production‑readiness expectations.
• Strong analytical and problem‑solving skills with the ability to convert operational issues into engineered solutions.
• Ability to work independently and collaboratively across global, cross‑functional teams.
• Strong written and verbal communication skills with the ability to explain technical concepts to non‑technical stakeholders.

Preferred Qualifications

• Experience building GenAI, LLM, RAG, chatbot, Copilot Studio, agentic workflow, or AI‑assisted automation solutions.
• Hands‑on experience with agent orchestration frameworks such as LangChain, LangGraph, CrewAI, AutoGen, Semantic Kernel, or similar technologies.
• Familiarity with Visa Agentic Toolchain concepts, including persistent sessions, shared context, quality gates, reusable artifacts, human approval points, and telemetry‑driven outcomes.
• Experience with ServiceNow, Jira, GitHub, Azure DevOps, Power Platform, Copilot Studio, observability platforms, endpoint telemetry, or enterprise support data.
• Experience with reliability engineering, incident management, problem management, root‑cause analysis, or operational automation.
• Experience building dashboards, reports, or metrics to demonstrate automation effectiveness and business impact.
• Familiarity with Model Context Protocol (MCP), tool‑calling patterns, function calling, and multi‑agent architectures.
• Experience with CI/CD pipelines, automated testing, release validation, or controlled deployment processes.
• Understanding of ITIL practices, enterprise change management, support workflows, and service reliability principles.
• Experience working with vector databases, embeddings, semantic search, and knowledge retrieval systems.
• Ability to identify repeatable support patterns and convert them into scalable automation.
• Curiosity and adaptability in learning emerging AI, automation, and reliability engineering practices.

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.