Senior Staff AI-Native Software Engineer – Agentic Systems

ServiceNow•Santa Clara, CA

9d•$201,300 - $352,300•Hybrid

About The Position

PLATO (Platform Engineering and AI Technology Organization) is the customer-obsessed engineering group building the agentic AI and enterprise-scale search systems that power Now Assist, AI Agents, and the AI-driven experiences our customers rely on every day. We build AI as foundational platform infrastructure — prioritizing robustness, performance, safety, and real-world customer impact at scale. AI Engineering and Delivery is the customer-obsessed engineering group building the agentic AI and enterprise-scale search systems that power Now Assist, AI Agents, and the AI-driven experiences our customers rely on every day. We build AI as foundational platform infrastructure — prioritizing robustness, performance, safety, and real-world customer impact at scale. You will design, build, and operate production-grade agentic AI systems embedded across ServiceNow's platform — autonomous agents that reason over real enterprise data, take action across workflows, and run safely at Fortune 500 scale. Your core focus areas: Agentic architecture. Design and ship multi-agent systems — orchestration, tool use, planning loops, memory, and failure recovery — that operate reliably in production, not in notebooks. Enterprise-grounded reasoning. Build agents that leverage ServiceNow's data layer — CMDB, Workflow Data Fabric, and Knowledge Graph — to make decisions with context no frontier model has on its own. Trust, safety, and governance. Own the guardrails: observability, human-in-the-loop controls, and compliance infrastructure that make autonomous systems safe to deploy at scale. Retrieval and grounding. Work closely with our search team to ensure agents are grounded in accurate, low-latency retrieval — RAG pipelines, hybrid search, re-ranking, and evaluation — as a critical dependency of agentic quality. Model integration and evaluation. Integrate frontier models (Anthropic, Google, OpenAI) into the Sense → Decide → Act → Govern architecture; evaluate trade-offs across cost, latency, and capability for production use cases. Engineering leadership. Raise the technical bar through architecture decisions, code reviews, and coaching — particularly on agentic design patterns and production AI discipline.

Requirements

8+ years of software engineering with strong fundamentals in data structures, algorithms, and distributed systems.
Hands-on depth designing, shipping, and operating agentic systems in production — multi-agent orchestration, tool calling, planning loops, memory, and failure recovery. Not prototypes.
Production-grade Python.
Working experience with frontier AI SDKs (Anthropic, Google, or OpenAI) — prompt engineering, structured outputs, and model evaluation in production settings.
Familiarity with RAG and retrieval patterns in production — vector stores, hybrid search, and retrieval evaluation metrics.
Track record of technical leadership: architecture ownership, code quality bar-raising, and mentoring engineers on production AI practices.

Nice To Haves

Deeper specialization in search and retrieval at scale or MLOps/model observability.
Published work or open-source contributions in agentic systems or retrieval.
Exposure to LLM fine-tuning or inference optimization in production.
Systems language (Go, Java, or C++) is a plus.

Responsibilities

Design and ship multi-agent systems — orchestration, tool use, planning loops, memory, and failure recovery — that operate reliably in production, not in notebooks.
Build agents that leverage ServiceNow's data layer — CMDB, Workflow Data Fabric, and Knowledge Graph — to make decisions with context no frontier model has on its own.
Own the guardrails: observability, human-in-the-loop controls, and compliance infrastructure that make autonomous systems safe to deploy at scale.
Ensure agents are grounded in accurate, low-latency retrieval — RAG pipelines, hybrid search, re-ranking, and evaluation — as a critical dependency of agentic quality.
Integrate frontier models (Anthropic, Google, OpenAI) into the Sense → Decide → Act → Govern architecture; evaluate trade-offs across cost, latency, and capability for production use cases.
Raise the technical bar through architecture decisions, code reviews, and coaching — particularly on agentic design patterns and production AI discipline.