Текст заказа
Our Mission
At Palo Alto Networks, we’re united by a shared mission—to protect our digital way of life. We thrive at the intersection of innovation and impact, solving real-world problems with cutting-edge technology and bold thinking. Here, everyone has a voice, and every idea counts. If you’re ready to do the most meaningful work of your career alongside people who are just as passionate as you are, you’re in the right place.
Who We Are
In order to be the cybersecurity partner of choice, we must trailblaze the path and shape the future of our industry. This is something our employees work at each day and is defined by our values: Disruption, Collaboration, Execution, Integrity, and Inclusion. We weave AI into the fabric of everything we do and use it to augment the impact every individual can have. If you are passionate about solving real-world problems and ideating beside the best and the brightest, we invite you to join us!
We believe collaboration thrives in person. That’s why most of our teams work from the office full time, with flexibility when it’s needed. This model supports real-time problem-solving, stronger relationships, and the kind of precision that drives great outcomes.
Job Summary
About the Role
We are looking for a Staff AI Engineer to be the technical anchor for Agentic AI in IT Quality Engineering – setting the architecture, standards and roadmap for 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 decide how agents plan, act, retrieve context and hand back to a human across these systems; how they are evaluated, governed and operated in production; and how the wider engineering team builds them well. This is a hands-on role: you will still design and write the hardest parts yourself.
At Palo Alto Networks we are moving towards an AI-First engineering culture. You will shape the direction of our own internal AI platform tools for test generation, automation scripting, execution and quality reporting, and lead the engineers who build on them.
KEY RESPONSIBILITIES
Architecture & Technical Direction
Agentic Architecture: Define the reference architecture for agentic systems across the landscape — planner-executor orchestration, multi-agent coordination, state, memory and recovery — and choose frameworks such as LangGraph, ADK, LangChain, LlamaIndex, AutoGen or CrewAI on evidence rather than fashion.
Event-Driven Enterprise Integration: Architect event-driven pipelines that connect Salesforce (Platform Events, Change Data Capture, Apex, Flows), SAP (OData/BAPI services and business-object events) and custom Licensing, Entitlement, AI Custom Quoting, Provisioning and ITSM applications to AI processing with production OAuth2 lifecycle, least-privilege access and idempotent writes to systems of record.
Context & Knowledge Architecture: Set the retrieval strategy across the estate — vector and graph stores (pgvector, Pinecone, Weaviate or Milvus; Apache AGE or Neo4j), advanced topologies (Graph RAG, Corrective RAG, HyDE, agentic retrieval), and the ingestion, freshness and access-control rules that keep context correct.
Tool & Protocol Standards: Own the standards for tool definitions, JSON function schemas and MCP servers across teams, so that agent tool calls are schema-validated, auditable and traceable back to Jira.
Model Strategy: Decide when prompting and retrieval are enough and when model customisation is justified — and lead resource-efficient fine-tuning (LoRA) where it is.
Quality, Safety & Governance at Scale
Evaluation Strategy & Release Gates: Define how AI agents — ours and the ones other teams build that the business depends on — are evaluated before release: golden sets, calibrated LLM-as-judge, adversarial testing, and risk-tiered release gates that block what should be blocked.
Autonomy & HITL Governance: Set the autonomy model — which decisions an agent may take alone, which need human approval, and how that changes as evidence accumulates — and make sure it is enforced in code, especially where agents write to systems of record.
LLMOps & Platform Reliability: Architect secure AI gateways, token-budget and rate-limit controls, model deployment pipelines, drift monitoring and automated rollback; own service levels, cost and incident response for production agents.
Responsible AI & Data Governance: Partner with security and data-governance owners to define guardrails on intellectual property and data privacy — managed secrets, explicit opt-in for any step that sends content to an external service, and an audit trail a reviewer can follow.
Leadership & Influence
Design & Review Board: Lead design reviews for agentic and AI-integrated systems across Salesforce, SAP and custom platforms, and set the code and design standards for both human-written and AI-generated code.
Roadmap & Strategy: Partner with engineering leadership, QE leads, product managers and enterprise architects to turn quality and business goals into a sequenced AI engineering roadmap — and say plainly what will not work.
Mentorship & Capability Building: Mentor Senior AI Engineers and AI Engineers, grow the next AI Architects, and shape the reference implementations and training that move engineers up our AI capability ladder.
Cross-Organisation Influence: Represent IT Quality Engineering in enterprise architecture and AI governance forums, and drive adoption of AI-native engineering practice beyond your own team.
Qualifications
Required Skills & Experience
Experience: 7–10 years of professional software engineering experience, including 3+ years in applied AI/ML, of which at least 2 years building LLM-based or agentic systems that reached production.
Leadership Track Record: 2+ years as a technical lead, staff engineer or architect driving architectural decisions and leading cross-functional technical initiatives to production.
Programming Mastery: Expert proficiency in Python and strong proficiency in Java or TypeScript/Node.js; excellent software design is a given.
Agentic Systems Architecture: You have designed and led production agentic systems — planner-executor orchestration, multi-agent coordination, state and memory, HITL control — and can explain the trade-offs you made and what you would change.
Distributed & Event-Driven Systems: Deep experience with microservices, event-driven architecture and message queues (e.g., Kafka, Pub/Sub), including idempotency, ordering, back-pressure and failure recovery.
Retrieval at Scale: You have designed production RAG systems over vector and/or graph stores, including access-controlled ingestion and measured retrieval quality.
Evaluation & Governance: You have established evaluation and release-gating practice for LLM systems — golden sets, LLM-as-judge calibration, adversarial and prompt-injection testing — that was adopted beyond your own team.
Enterprise Integration: Deep experience integrating with enterprise platforms — Salesforce, SAP or comparable CRM, ERP or ITSM systems — including OAuth2 lifecycle, safe write patterns and data-governance constraints.
Cloud, LLMOps & CI/CD: Strong experience with GCP/AWS/Azure, Docker and Kubernetes, CI/CD at enterprise scale, and operating AI services with observability, cost controls and rollback.
AI-Assisted Development: Deep fluency with tools such as Cursor, Claude Code or GitHub Copilot, and a track record of setting team practice for reviewing what they produce.
Education: B.E./B.Tech/M.Tech in Computer Science, Computer Engineering or a related technical field (or equivalent practical experience).
Preferred Qualifications
Model Customisation: Hands-on fine-tuning with resource-e