Senior Principal AI Engineer

Job Description Vertex is seeking a   Senior   Principal AI Engineer to define and build the foundational enterprise AI platform that powers intelligent applications across the enterprise. This role will lead the design and implementation of scalable, secure, and reusable capabilities for agentic AI, with a strong focus on retrieval-augmented generation (RAG), orchestration frameworks, evaluation systems, and platform architecture.   In addition to building out the core platform, this   engineer   will own the vision   and day-to-day operations of   a centralized AI   Gateway   / Control Plane /   Control Tower   that enables agent monitoring, observability, policy enforcement, governance, and operational controls across AI solutions at Vertex. This is a highly strategic and hands-on role for an experienced AI   engineer   who is excited to shape enterprise AI architecture, standards, and long-term technical direction.   Key Responsibilities   Agentic AI platform :   the shared architecture, services, and reusable capabilities that make it faster and safer to build AI-powered applications across Vertex   AI Control Tower operations: standing up and running the centralized control plane for agent monitoring, observability, telemetry, policy enforcement, guardrails, usage analytics, and auditability   Own the strategy, architecture, implementation, and day-to-day operation of the centralized AI Gateway / Control Tower as the enterprise control point for model access, routing, governance, cost management, and operational oversight   Intelligent model routing, provider abstraction, fallback, failover, rate limiting, and workload optimization across approved models   AI FinOps, including token and consumption visibility, budgeting, chargeback/ showback , cost allocation, forecasting, and model-cost optimization   Centralized guardrails for content safety, prompt-injection defense, data-loss prevention, sensitive-data handling, and responsible AI policy enforcement   Identity, access, security, privacy, regulatory compliance, and lifecycle governance controls for models, agents, tools, and AI interactions   End-to-end observability, telemetry, quality monitoring, latency and reliability metrics, incident response, and operational health management   Usage analytics, immutable audit trails, policy evidence, risk reporting, and executive-level transparency across the enterprise AI estate   Model onboarding, approval, versioning, deprecation, resiliency, capacity management, and third-party provider governance   Retrieval and knowledge systems: RAG pipelines, vector search, document retrieval, and the grounding patterns that make enterprise content usable by agents   Agent lifecycle and quality: deployment, versioning, evaluation frameworks, reliability measurement, and continuous improvement of agents in production   Standards and technical leadership: platform APIs, service contracts, architecture patterns, and the engineering practices other teams build against   Define the technical vision, architecture, and roadmap for Vertex’s enterprise agentic AI platform   Design and build reusable platform services that accelerate development of safe, reliable, and scalable AI-powered applications   Lead architecture and implementation for RAG pipelines, knowledge retrieval systems, prompt workflows, tool use, and agent orchestration   Establish core frameworks for agent lifecycle management, including deployment, monitoring, observability, evaluation, and continuous improvement   Develop scalable infrastructure patterns for enterprise AI workloads, including model integration, data access, and orchestration services   Partner closely with product, engineering, data, security, and UX teams to deliver common AI platform capabilities that support multiple use cases across Vertex   Establish best practices for AI reliability, evaluation, safety, and performance measurement   Drive technical standards for platform APIs, service contracts, architecture patterns, and reusable components   Evaluate emerging technologies, frameworks, and vendors in the AI/agentic ecosystem and make strategic recommendations   Mentor engineers and influence cross-functional technical teams through architectural leadership and hands-on guidance   Ensure platform solutions align with enterprise requirements for scalability, resilience, security, and maintainability   Contribute to Vertex’s long-term AI strategy by identifying opportunities to expand platform capabilities and increase enterprise adoption   Required Qualifications   Advanced degree in Computer Science, Engineering, Artificial Intelligence, Machine Learning, or a related technical field; or equivalent combination of education and experience   10 +   years   of   experience designing and building enterprise-grade AI/ML platforms and distributed systems   Deep expertise in agentic AI architectures, LLM-based applications, and platform engineering   Proven experience with retrieval-augmented generation (RAG) systems, vector search, document retrieval, and knowledge integration patterns   Strong experience with AI orchestration frameworks, workflow engines, and multi-step agent execution patterns   Demonstrated experience designing centralized operational platforms for monitoring, governance, observability, and control   Demonstrated experience using AI-assisted software development and autonomous coding agents to design, generate, test, review, debug, optimize, and refactor code across complex enterprise systems.    Deep understanding of AI-native software engineering practices and experience establishing standards, governance, and best practices for the responsible use of AI coding assistants and software engineering agents across engineering teams   Experience defining architecture, standards, and reusable services for large-scale enterprise environments