Staff Software Engineer (AI SW Integration - Prisma AIRS)

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

1d•$104,000 - $169,500•Onsite

About The Position

Join our team as a Backend AI Software Integration Engineer building a multi-tenant GenAI Security Platform that enables enterprises to benchmark, red-team, and secure LLMs and agentic workflows. In this core engineering role, you will focus predominantly on backend software development in Python—building middleware APIs, data ingestion endpoints, and integration hooks to embed Palo Alto Networks Prisma AIRS across enterprise AI pipelines and partner architectures.

Requirements

1+ years in Software Engineering or Systems Integration with a primary emphasis on backend development and cloud security.
Production-level mastery of Python for asynchronous backend services, API frameworks (FastAPI, Flask, or gRPC), and microservice architectures.
Experience developing, debugging, and integrating enterprise APIs (REST, gRPC, WebSockets) and API gateways (e.g., Envoy, Kong).
Experience writing code to map, translate, and standardize mismatched data formats between systems.
Experience building robust middleware, webhooks, and retry logic to handle high-volume sync traffic and system failures.
Practical experience integrating LLM APIs, vector storage, and agentic protocols/frameworks (LangChain, LlamaIndex, MCP) via backend middleware.
Proven ability to create technical architecture blueprints (e.g., Lucidchart) and secure AI workloads against prompt injection and model vulnerabilities. Rapid mastery of Prisma AIRS.
Experience using testing frameworks (e.g., PyTest, unittest) and robust evaluation workflows for distributed systems.
Excellent customer focus, collaboration and communication skills
BS/MS Computer Science, Computer Engineering, or related technical field or equivalent or equivalent military experience

Nice To Haves

Strong background in distributed task queues (e.g., Celery, Redis, RabbitMQ) and event-driven backend architectures.
Hands-on experience with automated AI red teaming, prompt defense tools, and securing Model Context Protocol (MCP) server interactions.
Working knowledge of major enterprise platforms (e.g., ServiceNow, Databricks, Glean)

Responsibilities

Design, build, and maintain high-performance, asynchronous REST/gRPC microservices, background job workers, and database schemas in Python.
Develop clean API endpoints, webhook receivers, and data ingestion hooks to collect, route, and inspect LLM prompts, context payloads, and agent execution logs.
Build middleware logic and AI Gateway integrations connecting model providers and agentic frameworks (LangChain, LlamaIndex, MCP) with inline security controls, policy enforcement, and fallback routing.
Author technical architecture diagrams and integration blueprints documenting insertion points for the Prisma AIRS portfolio (Model, Red Teaming, Runtime, and Agent Security) within cloud and hybrid environments.
Engineer programmatic execution pipelines for automated LLM probing (jailbreaks, prompt injections) and expose structured API endpoints to serve telemetry data to frontend dashboards and SIEM tools.
Review partner software architecture and provide documentation or SDKs to speed up integration timeline.