Sr Staff AI Engineer - Veza

Description

The Access AI team is an engineering group that builds the agentic AI and enterprise-scale harness platform used by agents for Access Management across the company's identity security products.

The team treats AI as core platform infrastructure, with a focus on robustness, performance, safety, and impact for customers at scale.

Responsibilities

• Architect, build, and run production agentic AI systems: autonomous agents that reason over enterprise data and carry out identity security actions for Fortune 500 customers.
• Shape architecture patterns, scalability guardrails, and long-term strategy for autonomous enterprise security as a senior technical leader working between agent research and large-scale backend systems.
• Design and ship multi-agent systems covering orchestration, tool use, planning loops, memory, and failure recovery, built to run reliably in production rather than in notebooks.
• Build agents that use Access Graph, Access Reviews, and permission and risk data to make decisions with context a frontier model lacks on its own.
• Own the guardrails for autonomous systems, including observability, human-in-the-loop controls, and compliance infrastructure.
• Work with product, platform, and graph teams to keep agents grounded in accurate, low-latency retrieval, covering RAG pipelines, semantic search, re-ranking, and evaluation.
• Integrate frontier models and weigh cost, latency, and capability trade-offs for production use cases.
• Raise the technical bar through architecture decisions, code reviews, and coaching, especially on agentic design patterns and production AI practice.

Requirements

• 8+ years of software engineering experience with strong fundamentals in data structures, algorithms, and distributed systems.
• Hands-on experience designing, shipping, and operating production agentic systems, including multi-agent orchestration, tool calling, planning loops, memory, and failure recovery.
• Production-grade Python. Experience with Go, Java, or C++ is a plus.
• Working experience with at least one frontier AI SDK (Anthropic, Google, or OpenAI), including prompt engineering, structured outputs, and model evaluation in production.
• Familiarity with production RAG and retrieval patterns, including vector stores, hybrid search, and retrieval evaluation metrics.
• A track record of technical leadership: owning architecture, raising code quality, and mentoring engineers on production AI practices.
• Deeper specialization in search and retrieval at scale or in MLOps and model observability is a plus.
• Published work or open-source contributions in agentic systems or retrieval is a plus.
• Exposure to LLM fine-tuning or inference optimization in production is a plus.

Conditions

Base pay ranges from $171,900 to $300,800, plus equity where applicable, variable or incentive compensation, and benefits.

Actual total compensation depends on factors such as qualifications, skill level, competencies, and work location, and the base pay shown is a guideline.

Pay is based on the geographic location of the role and may change depending on work location.

Work persona (flexible, remote, or required in office) is assigned based on the nature of the work and the assigned work location. The company may check the distance between your home and the nearest office using a third-party service.

Equal-opportunity policy applies.

Benefits

• Health plans, including flexible spending accounts.
• 401(k) plan with company match.
• Employee stock purchase plan (ESPP).
• Matching donations.
• Flexible time away plan and family leave programs.