Sr Principal AI Software Engineer / Generative AI Applications Architect (NetSec)

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 Your Career Palo Alto Networks is looking for a highly experienced, hands-on Senior Principal AI Software Engineer to architect and build the next generation of Generative AI applications and agentic systems across the enterprise. In this role, you will act as a senior technical leader responsible for defining and driving the architecture of AI-native applications that solve complex business problems through intelligent workflows, reasoning systems, and scalable distributed services. You will move beyond traditional software engineering to design and implement production-grade vertical AI applications that combine large language models, retrieval systems, structured and unstructured data reasoning, workflow orchestration, evaluation frameworks, and enterprise guardrails. You will partner closely with product, platform, security, data, and application teams to turn ambiguous opportunities into practical architectures and working systems. This is a deeply hands-on role for someone who can operate at both the strategy and implementation layers — shaping technical direction while also prototyping, reviewing, and guiding critical components into production. Your Impact Architect and build enterprise-grade Generative AI applications that combine LLMs, retrieval, structured data access, search, orchestration, and workflow automation. Design agentic systems and multi-step reasoning workflows using frameworks such as LangGraph or equivalent, with clear control over state, memory, tool invocation, and human-in-the-loop checkpoints. Build durable, fault-tolerant orchestration for long-running AI and business workflows using Temporal or similar workflow execution platforms. Define architectures that reason effectively across both structured and unstructured enterprise data, including relational data, APIs, knowledge bases, event streams, and document stores. Lead the design of retrieval pipelines that include lexical search, semantic search, vector search, metadata filtering, reranking, and hybrid retrieval strategies. Architect and optimize AI search experiences using platforms such as Elasticsearch, OpenSearch, and vector databases to support high-relevance, large-scale enterprise applications. Establish evaluation frameworks for LLM and agentic systems, including offline evals, regression suites, scenario-based testing, trace-level diagnostics, human review loops, and online quality metrics tied to business outcomes. Define and implement guardrails for AI applications, including prompt injection defenses, sensitive data protection, policy enforcement, grounding checks, output controls, and secure tool access boundaries. Drive reference architectures and reusable platform patterns for model routing, prompt and workflow ve ... (truncated, view full listing at source)