Apply on Employer Site

Palo Alto Networks · 1 day ago

Sr Principal AI Engineer (IT Go-To-Market & Customer Experience)

Santa Clara, CA

Full-time

Onsite

Senior Level, Lead/Staff

$223K/yr - $306K/yr

15+ years exp

Palo Alto Networks is a cybersecurity company focused on protecting digital lifestyles. They are seeking a Sr Principal AI Engineer to lead the design and implementation of advanced AI systems, particularly in the context of Go-To-Market processes and customer experience.

Cloud SecurityCyber SecurityNetwork SecuritySecurity

Growth Opportunities

No H1B

Responsibilities

Architect a Proxy-First AI Ecosystem: Lead the design and implementation of an "AI Gateway" intermediary layer to ensure vendor independence, allowing seamless switching between LLMs (e.g., GPT-4, Llama, Anthropic) without refactoring core application code

Unified API Design: Build a single, unified API endpoint that abstracts the complexities of individual LLM providers, providing centralized control for access and security

Deep System Visibility: Implement comprehensive observability pipelines specifically for GenAI to track trace-level data, prompt inputs/outputs, and model latency

Cost & Performance Optimization: Create architecture that optimize performance and expense by routing simpler queries to cost-effective models

Feedback Loops: Integrate observability data into the development cycle to identify bottlenecks, high-latency chains, and model drift in real-time

Agentic AI Leadership: Institute and promote innovative thinking by incorporating agentic AI, designing sophisticated Multi-Agent Systems and Agent-to-Agent (A2A) workflows

Business Workflow Automation: Apply GenAI to complex Go-To-Market (GTM) business logic, automating workflows such as customer support processes and entitlement platforms

Evaluation Frameworks: Pioneer "LLM as a Judge" testing methodologies to automate quality assurance, using capable models to evaluate the correctness, tone, and helpfulness of system outputs

AI Safety Implementation: Build robust guardrails to filter inputs and outputs, ensuring the prevention of PII exposure, offensive content, and prompt injection attacks

Adversarial Defense: Develop detection mechanisms including keyword filtering, behavioral analysis, and adversarial training to protect model instructions from manipulation

Qualification

AI ArchitectureGenAI StackLLM ObservabilityMulti-Agent SystemsPythonAgile/ScrumBusiness ProcessTesting & ValidationCommunication

Required

15+ years of overall IT system architecture, design, development, and deployment experience

Proven track record leading technical teams in Agile/Scrum environments for large-scale implementations with aggressive timeline

Experience partnering with business stakeholders to design workflows for Go-To-Market (GTM), sales, or support operations

Bachelor's degree or equivalent in Computer Science or a related field

Strong verbal and written communication skills with the ability to explain complex AI concepts to senior leadership

Extensive knowledge in building modern applications using Large Language Models (LLMs) such as Llama 3, GPT-4, and Anthropic

Deep experience building and maintaining highly observable systems

Proficiency with AI tracing and evaluation tools (e.g., LangSmith, Arize, HoneyHive, or custom OpenTelemetry implementations) to monitor hallucinations, latency, and token economics

Deep experience with Multi-Agent systems, Agent-to-Agent (A2A) communication, and orchestration frameworks

Experience establishing 'Golden Datasets' for ground truth testing and performing comparative analysis across different models

Expert-level proficiency in Python; familiarity with Java or Node.js for enterprise integration is a plus