Principal Engineer, AI Agentic Platform

Responsibilities

• Architect and evolve the AI Agentic Platform — defining the foundational layers for agent orchestration, tool use, memory, and multi‑agent coordination at Nordstrom scale
• Partner with AI/ML and product teams to translate business goals into platform capabilities that enable autonomous agent workflows across commerce, inventory, and customer experience domains
• Lead cross‑team design reviews, establish platform engineering standards, and create reusable architecture artifacts that accelerate delivery across the organization
• Apply deep AI fluency to evaluate and integrate LLM APIs, vector stores, RAG patterns, and emerging agentic frameworks (e.g., Lang Graph, Auto Gen, OpenAI Assistants API, Semantic Kernel)
• Mentor and coach engineers across teams; serve as the technical escalation point for complex agentic system issues and significant operational incidents
• Drive decisions on platform observability, evaluation, and guardrails — ensuring agents behave reliably, safely, and within business policy constraints
• Hands‑on POC development for novel agentic patterns to prove viability and inform broader team adoption
• Collaborate with senior technology and business leaders to articulate trade‑offs, influence roadmaps, and align platform strategy with Nordstrom’s long‑term AI vision
• Contribute to Nordstrom‑wide engineering standards, open‑source initiatives, and the broader AI engineering community

• 10+ years of professional software engineering experience
• AI Fluency —
  
  Required:
  
  Deep, hands‑on experience with LLMs, foundation model APIs (OpenAI, Anthropic, Google, etc.), prompt engineering, RAG architectures, and embedding‑based search in production environments
• Strong proficiency in Python and/or Java; experienced with cloud‑native development on AWS and/or GCP
• Expertise architecting complex, scalable distributed systems — microservices, event‑driven architectures, API gateways, and data pipelines
• Highly skilled at applying architectural patterns to express complex, scalable systems that optimize for simplicity, operational support, and implementation velocity
• Demonstrated experience influencing senior technical and business leaders, with the ability to clearly articulate engineering trade‑offs and drive cross‑team decisions
• Strong Dev Ops foundation — CI/CD (Git Lab or equivalent), containerization (Kubernetes/Docker), observability and telemetry, and SLA‑driven reliability engineering
• Experience with Agile methodologies, continuous improvement mindset, and security‑first development practices
• Track record of mentoring and growing engineering talent across multiple teams
• Bachelor’s or Master’s degree in Computer Science, Computer Engineering, or a related field