We are looking for an early-in-career AI Engineer to build and ship custom Agentic AI. Applications across an Enterprise IT landscape spanning Salesforce, SAP, custom. Licensing and Entitlement management applications, and AI Custom Quoting, Provisioning and ITSM platforms. You will work with modern generative AI — LLM orchestration, autonomous agent loops, tool calling and RAG — against real enterprise infrastructure, building agents that carry out multi-step business workflows, act on data across these systems through their APIs, and hand back to a human when they should.
At Palo Alto Networks we are moving towards an AI-First engineering culture, and you will not be starting from a blank page. You will build on our own internal AI platform tools for test generation, automation scripting, execution and quality reporting.
Agentic Systems & Enterprise Integration
Build agentic features: Develop and maintain agent workflows using LangGraph, ADK, LangChain, AutoGen or CrewAI, including planner/executor loops, state handling and failure recovery.
Enable cross-system integration and tool calling: Connect agents across enterprise applications, including: Salesforce: REST/SOAP APIs, Webhooks, Platform Events, Apex Invocable Methods, SOQL and Flows. SAP: OData/BAPI services and business-object events. Custom applications: Licensing, Entitlement, AI Custom Quoting, Provisioning and ITSM through REST APIs, webhooks and message queues.
Build context grounding and RAG pipelines: Use vector stores such as pgvector, Pinecone and Weaviate to provide LLMs with accurate, current enterprise context.
Define tools and schemas: Create well-specified tool definitions and JSON function schemas, including MCP tools, to support deterministic tool calls and traceability back to Jira.
Agent Quality, Safety & Observability
Build evaluation suites: Develop and run golden-set evaluations to validate improvements to agents and prompts before release.
Implement guardrails and human-in-the-loop workflows: Establish safety controls, rate limiting, fallbacks and clear approval handoffs, especially when agents write to systems of record.
Enable observability: Instrument agents with tracing and metrics covering execution paths, latency, context usage and token costs, and use findings to improve performance.
Apply responsible AI practices: Follow company policies on intellectual property and data privacy, keep secrets in managed stores and require explicit opt-in for steps that send content to external services.
Collaboration & Growth
Collaborate across functions: Partner with Salesforce, SAP and platform architects, QE leads, product managers and security teams to deliver reliable AI features that meet business, quality and enterprise compliance requirements.
Learn the enterprise landscape: Build an understanding of transaction flows from AI Custom Quoting and order capture through licensing, entitlement, provisioning and service management. Prior knowledge is not required, but proactive learning is expected.
Share knowledge: Contribute working examples, reusable tools and reviewed code to strengthen AI fluency across engineering teams.
Qualifications
Experience: 1–4 years of professional software engineering experience or equivalent demonstrable capability.
Programming: Strong proficiency in Python or TypeScript/Node.js, with sound fundamentals in data structures, testing and code review.
Backend fundamentals: Practical experience building and consuming REST APIs, working with relational databases and handling asynchronous or queue-based processing.
Hands-on LLM experience: Demonstrable experience with LLM APIs, including prompting, function/tool calling and structured outputs, through professional work, internships, open-source contributions or substantial personal projects.
Agentic or RAG exposure: Built at least one working agent or retrieval pipeline end to end, with the ability to explain its design, failures and improvements.
Integration skills: Comfortable reading unfamiliar enterprise API documentation and determining how to integrate safely.
Version control and CI: Comfortable using Git in a team environment and working with automated build and test pipelines.
AI-assisted development: Daily working fluency with tools such as Cursor, Claude Code or GitHub Copilot, with the judgement to critically review generated output.
Education: B.E./B.Tech/M.Tech in Computer Science, Computer Engineering or a related technical field, or equivalent practical experience.
Preferred Qualifications
Production agents: Experience deploying AI agents or LLM features into production, including multi-agent coordination or autonomous decision loops.
Enterprise application knowledge: Exposure to one or more of the following: Salesforce: REST/Composite/Bulk APIs, SOQL/SOSL, Connected Apps, OAuth and Apex. SAP: OData, BAPI/RFC, IDocs or business-object events. Enterprise platforms: AI Custom Quoting, Provisioning, Licensing/Entitlement or ITSM platforms and their supporting distributed services.
Vector databases and embeddings: Experience with semantic search, embedding generation and vector engines such as pgvector, Pinecone, Qdrant or ChromaDB.
Advanced retrieval: Familiarity with Graph RAG, Corrective RAG, HyDE or agentic retrieval, and graph stores such as Apache AGE or Neo4j.
Model Context Protocol: Experience authoring MCP servers, including tools, resources and prompts.
Cloud and DevOps: Exposure to GCP, AWS or Azure, containerisation using Docker or Kubernetes, and serverless computing. Vertex AI experience is a plus.
Test automation: Familiarity with Playwright, REST Assured, Selenium or PyTest.
Domain interest: Grounding in B2B sales processes, Partner Relationship Management (PRM) or the Quote-to-Cash lifecycle.
Ways of Working
Evidence over assertion: Measure results before and after changes, share findings with the methodology and clearly acknowledge inconclusive outcomes.
Curiosity with rigour: Explore new tools, validate them before adoption and understand the difference between a demo and a reliable system.
Ownership: Take tasks from ambiguity through delivery and raise blockers early.
Builder’s bias: Prioritise shipping focused, reliable capabilities that users can trust over broad features that only perform well in demonstrations.
Growth Path
Join at the AI Engineer tier of the internal AI capability ladder, between AI User and AI Architect.
Progress towards AI Architect, building expertise in: Planner–executor orchestration at scale. Multi-agent systems with human-in-the-loop controls. Event-driven integration across enterprise IT systems. Model customisation.
Access company-funded training to support this progression.
The Team
Join a growing, passionate and dynamic team working on challenging, mission-driven projects.
Contribute to a people-centric culture focused on creating an exceptional employee experience.
Help expand what is possible in the workplace through innovation and collaboration
Our Commitment
We’re trailblazers that dream big, take risks, and challenge cybersecurity’s status quo. It’s simple: we can’t accomplish our mission without diverse teams innovating, together.
We are committed to providing reasonable accommodations for all qualified individuals with a disability. If you require assistance or accommodation due to a disability or special need, please contact us at accommodations@paloaltonetworks.com.
Palo Alto Networks is an equal opportunity employer. We celebrate diversity in our workplace, and all qualified applicants will receive consideration for employment without regard to age, ancestry, color, family or medical care leave, gender identity or expression, genetic information, marital status, medical condition, national origin, physical or mental disability, political affiliation, protected veteran status, race, religion, sex (including pregnancy), sexual orientation, or other legally protected characteristics.
All your information will be kept confidential according to EEO guidelines.
Is role eligible for Immigration Sponsorship? No. Please note that we will not sponsor applicants for work visas for this position.
