SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Salary: USD 171,900 - 300,800 / annual
The Access AI team at ServiceNow (which acquired Veza in March 2026) is building agentic AI and enterprise-scale platform infrastructure for Access Management across Identity Security Products. You will architect, build, and operate production-grade agentic AI systems—autonomous agents that reason over enterprise data and execute mission-critical identity security actions at Fortune 500 scale.
As a tier-one technical leader at the intersection of agent research and large-scale backend systems, you will shape architectural patterns, scalability guardrails, and strategic vision for autonomous enterprise security.
Core focus areas include:
• Agentic architecture: Design and ship multi-agent systems covering orchestration, tool use, planning loops, memory, and failure recovery that operate reliably in production.
• Enterprise-grounded reasoning: Build agents that leverage Access Graph, Access Reviews, and permission/risk data to make decisions with context no frontier model has independently.
• Trust, safety, and governance: Own guardrails including observability, human-in-the-loop controls, and compliance infrastructure for safe deployment at scale.
• Retrieval and grounding: Work with product, platform, and graph teams to ensure agents are grounded in accurate, low-latency retrieval through RAG pipelines, semantic search, re-ranking, and evaluation.
• Model integration and evaluation: Integrate frontier models and evaluate trade-offs across cost, latency, and capability for production use cases.
• Engineering leadership: Raise technical bar through architecture decisions, code reviews, and coaching on agentic design patterns and production AI discipline.
Veza manages over 30 billion access permissions for global enterprises including Blackstone, Expedia, and Wynn Resorts. The role combines the scale and resources of an enterprise platform company with the product velocity and mission-driven focus of a security innovator.
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, failure recovery)—not prototypes
• Production-grade Python; systems language (Go, Java, or C++) is a plus
• Working experience with frontier AI SDKs (Anthropic, Google, or OpenAI) including prompt engineering, structured outputs, and model evaluation in production settings
• Familiarity with RAG and retrieval patterns in production (vector stores, hybrid search, retrieval evaluation metrics)
• Track record of technical leadership: architecture ownership, code quality bar-raising, and mentoring engineers on production AI practices
NICE TO HAVE:
• 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
