ServiceNow · Posted 10d ago
Senior Staff AI Engineer (Veza)
Job relayed by Stapply Data, its source: you apply there.
- Location
- 🇺🇸 Santa Clara, United States
- Contract
- Full-time
- Role
- ML engineering
- Source
- Stapply Data
Stack
- LLM
- Vector DB
- Python
- Java
- Go
- C++
The posting
Join the Access AI team, a customer-focused engineering group dedicated to building agentic AI and an enterprise-scale harness platform for Access Management across all Identity Security Products. As a Senior Staff AI Engineer, you will architect, build, and operate production-grade agentic AI systems that reason over enterprise data and execute mission-critical identity security actions at Fortune 500 scale. Your core focus areas will include agentic architecture, enterprise-grounded reasoning, trust, safety, and governance, retrieval and grounding, model integration and evaluation, and engineering leadership.
- Architect, build, and operate production-grade agentic AI systems, focusing on multi-agent systems and orchestration. - Design and implement enterprise-grounded reasoning for agents, leveraging Access Graph and permission data for decision-making. - Lead engineering efforts in trust, safety, and governance for autonomous systems, ensuring compliance and observability.
- 8+ years of software engineering with strong fundamentals in data structures, algorithms, and distributed systems - Familiarity with RAG and retrieval patterns in production — vector stores, hybrid search, and retrieval evaluation metrics - Production-grade Python. Systems language (Go, Java, or C++) is a plus - Working experience with frontier AI SDKs (Anthropic, Google, or OpenAI) — prompt engineering, structured outputs, and model evaluation in production settings - Track record of technical leadership: architecture ownership, code quality bar-raising, and mentoring engineers on production AI practices - Hands-on depth designing, shipping, and operating agentic systems in production — multi-agent orchestration, tool calling, planning loops, memory, and failure recovery. Not prototypes - Deeper specialization in search and retrieval at scale or MLOps/model observability - Exposure to LLM fine-tuning or inference optimization in production - Published work or open-source contributions in agentic systems or retrieval