Principal Product Manager

The role

This role leads the product direction for agentic AI systems, including agent chaining, a shared context graph, telemetry and evaluation, and a Model Workbench for marketers. The person aligns Product, Engineering, Data Science, Design, Analytics, Security and business teams around shared architecture and platform standards.

What you will do

• Develop and manage the architecture for chaining LLM agents, tools, models and workflows
• Lead the development of a shared Context Graph for agents
• Implement context streaming services with real-time awareness
• Define the telemetry framework and analyze agent performance in production
• Build agent evaluation suites for offline and production testing
• Lead the creation of a Model Workbench for non-technical users
• Oversee registration and governance of MCP servers, tools and agents
• Drive cross-functional alignment on architecture, standards and priorities
• Define platform standards for agents, tools, context and workflows
• Prototype rapidly and troubleshoot using tools such as LangSmith

Required qualifications

• Demonstrated experience leading complex technical products, such as LLMs, AI agents, workflow systems or ML infrastructure
• Strong understanding of LLM agents, tool use, orchestration and multi-agent workflows
• Experience with context graphs, knowledge graphs, semantic systems or memory architectures
• Strong understanding of telemetry, evaluation and observability for AI systems
• Exceptional ability to align senior stakeholders and cross-functional teams
• Systems thinking across product, models, data, infrastructure and operations
• Strong technical background with hands-on familiarity with LangSmith, APIs, workflow orchestration, MCP and evaluation frameworks
• Demonstrated ability to troubleshoot ambiguous problems and prototype solutions
• Excellent communication skills for technical and non-technical audiences

Nice to have

• Experience building or operating agentic infrastructure, AI platforms, context platforms, knowledge graphs or developer ecosystems
• Experience integrating traditional machine learning with generative models and agentic systems
• Experience with workflow orchestration platforms and distributed systems
• Experience designing AI telemetry, evaluation systems or experimentation frameworks
• Demonstrated success establishing cross-functional technical standards and governance
• Experience building systems where context, telemetry and evaluation form a continuous learning loop

Benefits

• Unlimited PTO
• Medical, dental and vision coverage
• Employee equity
• Employee discounts
• Virtual wellness classes
• Pet insurance

About the company

Zeta Global is an AI-powered marketing cloud, headquartered in New York City with offices around the world. The company was founded in 2007 by David A. Steinberg and John Sculley.