Senior Context Engineer, AI Systems

• Architect and optimize how MagicSchool's AI agents reason, remember, and operate within complex educational workflows
• Design context management systems that determine what information our agents see, how they maintain state across multi-turn interactions, and how they retrieve knowledge
• Implement the technical foundation of how AI agents manage their 'mental workspace'
• Design and implement context curation systems for product features
• Build memory compaction mechanisms and state management patterns
• Implement monitoring and evaluation for retrieval precision and reasoning coherence
• Build dynamic, runtime data fetching that enable agents to autonomously pull relevant curriculum content, student data, and educational resources
• Build token-efficient tool APIs and retrieval layers for product teams
• Partner with Product to translate educational workflows into optimal context configurations
• Work with evaluations researchers, platform engineers, and others to implement memory modules, retrieval adapters, and human-in-the-loop correction systems
• In collaboration with Product and peers, shape work for the team
• Coordinate with other squads on requirements, patterns, and integrated projects
• Share context engineering insights with the team

• 4+ years building distributed systems
• Hands-on experience with RAG systems, knowledge graphs, or semantic search platforms in production environments
• Strong coding skills in Python, TypeScript/Node.js
• Experience with our stack (TypeScript, Node.js, PostgreSQL, NextJS, Supabase) or similar
• Proficiency with LLM APIs (OpenAI, Anthropic, etc.) and their context management patterns
• Experience with Model Context Protocol (MCP), context window optimization for specific model families, or building context-aware agent frameworks
• Understanding of or interest in how educational content is structured (standards, curricula, taxonomies), privacy requirements (FERPA/COPPA), and how context needs differ across teaching scenarios
• Experience with agent evaluation, measuring context quality/relevance, or instrumentation for attention budget tracking

Knowledge of curriculum standards, learning progressions, or educational metadata schemas that inform context design

• Unlimited time off
• Choice of employer-paid health insurance plans
• Dental and vision offered at very low premiums
• Generous stock options, vested over 4 years
• 401k match
• Monthly wellness stipend