Sr. Staff Software Engineer (AI Platform)

Palo Alto Networks•Office - USA - CA - Headquarters, CA

17d•$153,700 - $248,600•Onsite

About The Position

As a Sr. Staff Software Engineer (AI Platform), you will design, architect, and build intelligent software applications, agentic workflows, and production-ready LLM integrations across our product ecosystem. Leveraging cutting-edge AI technologies, you will engineer autonomous software agents, implement custom LLM pipelines, and integrate predictive analytics directly into core applications to automate complex operations. This role is pivotal in driving our next-generation software architecture by bridging state-of-the-art AI model capabilities with scalable application environments.

Requirements

8+ years of experience in Software Engineering, Platform Engineering, or Distributed Systems with a Bachelor’s degree in a technical field.
2+ years of hands-on experience building AI software, integrating LLMs, or developing predictive analytics into production applications.
Proven track record with LLM APIs & SDKs (OpenAI, Anthropic, Google Vertex AI, AWS Bedrock) alongside practical prompt engineering and agent framework development.
Strong software engineering fundamentals in Python, TypeScript (Node.js), or Go.
Deep understanding of software architecture, asynchronous programming, distributed systems design, and performance tuning.

Nice To Haves

Experience with multi-cloud infrastructure (AWS, Azure, GCP) and Infrastructure-as-Code tools (Pulumi, AWS CDK, Terraform).
Deep understanding of Kubernetes, service meshes, and cloud-native networking dynamics.
Background in Linux internals, low-level system performance tuning, or core SRE practices.
Experience building intelligent CI/CD delivery pipelines (GitHub Actions, GitLab CI) with AI-assisted code reviews.
Certified Kubernetes Administrator (CKA) or equivalent cloud architecture certifications.

Responsibilities

Architect AI-Driven Systems: Design and build production-grade software applications, agentic workflows, and custom LLM integrations using Python, TypeScript, or Go.
Engineer Autonomous Agents: Develop intelligent, self-executing software agents to automate complex operational tasks, drift detection, and application workflows.
Integrate Predictive Analytics: Leverage predictive machine learning models to analyze application performance, system behavior, and operational spend patterns in real time.
Build Next-Gen Observability & Security Tools: Implement intelligent observability frameworks and AI-driven automation for automated auditing and code/vulnerability patching via LLM interfaces.
Bridge AI & Platform Architecture: Partner closely with Core AI/ML teams to translate frontier models into high-availability, high-throughput software services.
Design Root Cause Analysis Workflows: Architect internal AI agents and diagnostic tools for automated Root Cause Analysis (RCA) and system.