Senior Product Manager, Context Engineering

ZoomInfo is a Go-To-Market Intelligence Platform that empowers businesses to grow faster with AI-ready insights. The Senior Product Manager for Context Engineering will architect the context layer powering AI intelligence across various platforms, transforming how workflows access and deliver information while ensuring quality and performance.

Responsibilities:

• Architect Context Acquisition Pipelines Design and optimize how ZoomInfo retrieves, transforms, and delivers context from our semantic data layer, memory systems, and data producers. You'll balance retrieval quality against latency and cost constraints, implementing hybrid search strategies, intelligent caching, and context compression techniques that maintain information density while respecting token budgets
• Own the Context Layer Platform Build infrastructure serving multiple product teams—Copilot, GTM Studio, MarketingOS—as internal customers. Establish API contracts, developer experience standards, and integration patterns that accelerate feature velocity. Maintain the delicate balance between providing flexible building blocks and opinionated solutions that encode best practices
• Drive Quality Through Measurement Implement evaluation frameworks using RAGAS metrics and custom benchmarks. Monitor retrieval precision, context relevance, hallucination rates, and system performance in production. Translate quality signals into architectural improvements, working closely with ML engineers to iterate on embedding models, reranking strategies, and retrieval algorithms
• Navigate Emerging Research Context engineering evolves weekly. You'll continuously evaluate innovations—GraphRAG for multi-hop reasoning, test-time compute scaling, multimodal retrieval, compression techniques—determining which advances warrant production investment versus which remain academic curiosities. Bring external best practices to ZoomInfo while contributing learnings back to the broader community
• Orchestrate Cross-Functional Execution Translate between three distinct worlds: ML engineers optimizing retrieval algorithms, platform engineers building scalable infrastructure, and product teams shipping customer features. Establish communication cadences, prioritization frameworks, and decision-making processes that balance urgent requests against strategic platform development

Requirements:

• 4-6 years of product management experience with 2+ years in ML/AI infrastructure
• Direct experience with production RAG systems, vector databases, or semantic search, context management
• Experience with graph databases (e.g. Neo4j)
• Track record building platform products serving multiple internal or external customers
• Familiarity with context compression, embedding models, and retrieval evaluation frameworks
• History of defining product vision in nascent technical domains where best practices are still emerging
• Expert-level understanding of RAG system architecture
• Python and SQL proficiency
• Experience building infrastructure products where internal engineering teams are your customers
• You measure success through downstream product velocity improvements and developer satisfaction scores
• You understand platform economics
• You read recent research papers from arXiv, ACL, NeurIPS
• You prototype emerging techniques to understand their practical constraints
• You maintain strong opinions weakly held
• You can explain to executives why implementing GraphRAG takes 6 months but unlocks $10M in product capabilities
• You can communicate to engineers why business constraints require shipping 'good enough' in 3 weeks rather than 'optimal' in 3 months
• You influence without formal authority through data, clear reasoning, and earned credibility