Apply on Employer Site

MagicSchool AI · 2 months ago

Senior Context Engineer, AI Systems

United States

Full-time

Remote

Senior Level, Lead/Staff

$160K/yr - $190K/yr

7+ years exp

MagicSchool is the premier generative AI platform for teachers, aiming to create real social impact in education. The Staff Context Engineer for AI Systems will architect and optimize AI agents' reasoning and memory across complex educational workflows, ensuring reliable assistance for millions of educators.

Artificial Intelligence (AI)E-LearningEdTechEducation

Responsibilities

Architect and implement adaptive context curation pipelines that determine what information enters each agent inference step, balancing comprehensiveness with the finite attention budget of LLMs to prevent context rot

Invent and operationalize memory compaction mechanisms and state management patterns that allow agents to maintain coherence across extended teaching workflows (lesson planning, differentiation, assessment creation)

Design evaluation pipelines that measure retrieval precision, token relevance, and reasoning coherence as context evolves across sessions. Work with the evaluations team on developing frameworks for measuring attention allocation and agent performance degradation

Build dynamic, runtime data fetching systems that enable agents to autonomously pull relevant curriculum content, student data, and educational resources exactly when needed, rather than pre-loading context with unnecessary information

Engineer token-efficient tool APIs and retrieval layers where each tool earns its place in the context window through clear utility and minimal overlap, with robust metadata to guide agent decision-making

Partner with Product, Research, and Education teams to translate complex educational workflows into optimal context configurations, understanding which information signals matter most for different teaching scenarios

Collaborate with ML researchers and platform engineers to co-design architectures that integrate memory modules, retrieval adapters, and human-in-the-loop correction systems

Guide engineers on context engineering patterns, teaching the shift from prompt-first thinking to holistic context management, token budget awareness, and dynamic information curation

Qualification

Context Engineering ExpertiseDeep Systems & AI ExperienceTechnical StackInformation ArchitectureEducational Context AwarenessLeadership & ImpactTechnical MentorshipCross-Functional Collaboration

Required

Deep Systems & AI Experience: 7+ years building distributed systems with at least 3+ years in staff/senior roles. Hands-on experience building LLM applications, agentic systems, or context-heavy AI workflows with clear understanding of transformer architectures and attention mechanisms

Context Engineering Expertise: Demonstrated experience managing context windows, building dynamic retrieval mechanisms, or designing context compaction strategies. Understanding of when context becomes a liability vs. an asset

Technical Stack: Strong coding skills in TypeScript/Node.js with Python as a nice addition. Experience with our stack (TypeScript, Node.js, PostgreSQL, NextJS, Supabase) or similar. Familiarity with LLM APIs (OpenAI, Anthropic, etc.) and their context management patterns

Information Architecture: Understanding of information retrieval, structured data representation, and strategies for organizing knowledge for AI consumption

Educational Context Awareness: 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

Leadership & Impact: Track record of architecting information systems, making high-leverage architectural decisions, and mentoring engineers on sophisticated technical concepts

Preferred

Experience with Model Context Protocol (MCP), context window optimization for specific model families, or building context-aware agent frameworks

Familiarity with educational technology platforms, curriculum databases, or EdTech content management

Background in semantic search or hybrid retrieval systems

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

Benefits

Flexibility of working from home, while fostering a unique culture built on relationships, trust, communication, and collaboration with our team - no matter where they live.

Unlimited time off to empower our employees to manage their work-life balance. We work hard for our teachers and users, and encourage our employees to rest and take the time they need.

Choice of employer-paid health insurance plans so that you can take care of yourself and your family. Dental and vision are also offered at very low premiums.

Every employee is offered generous stock options, vested over 4 years.

Plus a 401k match & monthly wellness stipend