Senior Product Manager - AI Agents

Zeta Global•New York City, NY

2d•$170,000 - $180,000

About The Position

Zeta Global (NYSE: ZETA) is the AI-Powered Marketing Cloud that leverages advanced artificial intelligence (AI) and trillions of consumer signals to make it easier for marketers to acquire, grow, and retain customers more efficiently. Through the Zeta Marketing Platform (ZMP), our vision is to make sophisticated marketing simple by unifying identity, intelligence, and omnichannel activation into a single platform – powered by one of the industry’s largest proprietary databases and AI. Our enterprise customers across multiple verticals are empowered to personalize experiences with consumers at an individual level across every channel, delivering better results for marketing programs. Zeta was founded in 2007 by David A. Steinberg and John Sculley and is headquartered in New York City with offices around the world. To learn more, go to www.zetaglobal.com . Zeta Global is on the cutting edge of integrating large language models (LLMs) into marketing technology. We are seeking a Product Manager to lead our LLM Operations, focusing on agent chaining, model orchestration, and the development of a marketer-friendly agentic tooling. This role is pivotal in making advanced LLM capabilities accessible to marketers in-line and as dedicated product offerings, bridging the gap between technical complexity and user-friendly applications.

Requirements

Experience in Product Management: Demonstrated experience managing complex technical products, particularly those involving LLMs or AI-driven tools.
Technical Proficiency: Strong technical background with hands-on experience in tools like LangSmith, and familiarity with workflow orchestration and LLM agent chaining.
Problem-Solving Skills: Proven ability to troubleshoot, innovate, and rapidly prototype solutions to demonstrate product feasibility.
Communication and Collaboration: Excellent communication skills, with the ability to work closely with cross-functional teams and offshore developers to align on best practices and product goals.

Nice To Haves

Experience with Agentic Infrastructure: Familiarity with integrating traditional ML with generative models to enhance model explainability and user interaction.
Background in Workflow Orchestration: Experience with existing workflow orchestration tools and methodologies.

Responsibilities

Agent Chaining and Orchestration: Develop and manage the process of chaining LLM agents for complex workflows, ensuring seamless orchestration and integration within our platform.
Model Workbench Development: Lead the creation of a Model Workbench designed for marketers, making it intuitive for non-technical users to leverage LLM capabilities in their workflows.
MCP Capabilities: Oversee the registration and maintenance of Model Context Protocol server, ensuring that all model capabilities are well-documented and easily accessible.
Agent Evaluation Suites: Build robust evaluation suites for testing and iterating on agent performance, ensuring continuous improvement and reliability.
Context Streaming Services: Implement and manage context streaming services that allow for real-time data flow and contextual awareness in agent interactions.
Technical Troubleshooting and Prototyping: Actively participate in troubleshooting and debugging using tools like LangSmith, and lead by example in building proof-of-concepts (POCs) to demonstrate the feasibility and potential of new ideas.
Advocacy for Quick Iteration: Promote a culture of rapid prototyping and iteration, demonstrating the value of "vibe coding" as a gateway to scalable product development.