Senior Product Manager - AI Systems & Context

WHO WE ARE: Magic School is the premier generative AI platform for teachers. We're just over 2 years old, and more than 7 million teachers from all over the world have joined our platform. Join a top team at a fast growing company that is working towards real social impact. Make an account and try us out at our website and connect with our community on our Wall of Love.

As a Senior Product Manager for AI Systems & Context, you will define how Magic School’s AI agents think, reason, retrieve information, and maintain coherence across complex educational workflows. You’ll translate company vision and goals into a product strategy that applies deep systems, retrieval, and knowledge-graph concepts to context, memory, and retrieval foundations that power intelligent, reliable agentic behavior for millions of educators.

• Define and own the product strategy for context, memory, and retrieval systems that determine what information AI agents see, how they maintain continuity, and how they ground responses from structured and unstructured data.

• Partner with Context Engineering and Knowledge Graph Engineering to translate advanced technical capabilities - dynamic retrieval, context compaction, graph-powered reasoning - into clear product requirements, evaluation frameworks, and shipped features.

• Drive end-to-end development of context pipelines and AI reasoning systems to ensure products balance token efficiency, retrieval precision, and real-world classroom reliability.

• Design measurement frameworks for context quality, retrieval performance, knowledge grounding, and long-horizon coherence; use these to prioritize improvements and safeguard product correctness.

• Represent educators and classroom workflows with deep empathy and collaboration, defining which information and tools are needed to power effective AI assistance across lesson planning, differentiation, assessment, and complex multi-step tasks.

• 5+ years of product management experience
  , including ownership of platform, AI systems, agentic workflows, retrieval systems, or technically complex backend products.

• Strong understanding of AI context management
  , including experience with LLMs, agent architectures, prompt strategies, context windows, embeddings, retrieval-augmented generation (RAG), memory systems, or structured knowledge representations.

• Technical fluency with data systems
  , with familiarity in knowledge graphs, database optimization, entity/relation modeling, retrieval pipelines, and relevance/tuning concepts.

• Ability to partner deeply with engineering
  , translating distributed systems constraints, retrieval models, and graph architectures into product strategy and requirements.

• Experience using both qualitative and quantitative data (eval metrics, retrieval quality, latency, token usage, performance degradation) to drive product decisions.

• Exceptional execution and prioritization skills
  , especially in highly technical environments with complex interdependencies across engineering, research, and platform teams.

• Clear, persuasive communication skills
  , able to align partners across engineering, research, education, and product on highly technical concepts.

• Experience shipping platform-level or AI/ML-driven systems involving context, retrieval, or structured information.

• Hands-on work with LLM-based products, ideally including RAG architectures, memory systems, vector search, or dynamic retrieval.

• Demonstrated experience working closely with data engineering teams, with familiarity in concepts like:

  • knowledge graphs

  • entity linking

  • schema design

  • database/query optimization

  • semantic search patterns

• Strong background working within complex technical stacks (Python, Type Script/Node.js, relational databases, vector databases, or equivalent).

• Proven track record driving measurable improvements in system quality, reliability, or correctness.

• Direct experience with knowledge…