Senior Software Engineer (AI Applications)

Job Overview Are you driven to build innovative, intelligent systems that fundamentally change how people learn? Join our team of engineers and researchers at the forefront of educational technology to design and deploy the next generation of AI-powered solutions. Cambium Assessment Inc is a leading education technology firm with a growing software engineering and product development team. We design and build online assessment systems that are used by millions of students providing actionable insights for educators grounded in scientific theory. We are seeking a Lead/Senior Software Engineer (AI Applications) to own the architecture and implementation of reliable and responsible agent orchestration systems. In this high-impact, individual contributor role, you will be instrumental in designing autonomous AI agents, integrating advanced generative capabilities into our core products, and establishing the technical foundation for our AI-driven future. You will be a key technical leader, driving best practices, mentoring peers, and ensuring our AI systems are scalable, safe, and trustworthy. Job Responsibilities: Agent Architecture & Implementation: Design, build, and deploy robust Generative AI agents featuring advanced capabilities like persistent memory, shared state management, and complex multi-step reasoning workflows specifically tailored for real-world educational applications. Product Innovation: Drive the development of cutting-edge, AI-enabled web based educational software systems that redefine user interaction and learning outcomes. Generative AI Integration: Seamlessly incorporate Generative AI features into existing platforms, focusing on optimizing performance, ensuring a seamless UX, and maintaining strict safety compliance. Intelligent System Leverage: Expertly leverage Large Language Models (LLMs) and multimodal models to deliver highly intelligent, context-aware user experiences. Agent Quality & Evaluation: Establish and maintain frameworks for comprehensive agent evaluation, including rigorous testing, critical safety assessments, and detailed performance monitoring. Cross-Functional Leadership: Partner closely with other teams to translate complex user needs and learning workflows into scalable, production-ready agentic capabilities. Technical Mentorship: Act as a subject matter expert, guiding engineers on advanced agent design patterns, optimal LLM integration strategies, and best practices for building secure, autonomous systems. Mission Alignment: Contribute to a mission-driven environment focused on innovation, measurable impact, and the ethical, responsible development and deployment of AI enabled products. Job Requirements: Experience : 5+ years in software engineering, including 2+ years in a Senior/Staff-level capacity leading significant technical initiatives. Agentic Systems Mastery : Proven, hands-on experience building complex agentic systems, including proficiency with tool calling, advanced prompt optimization, and comprehensive context engineering. LLM Integration & Backend : Deep, practical experience integrating with LLMs, coupled with strong skills in prompt engineering and Retrieval-Augmented Generation (RAG) pipelines. Programming Proficiency : Strong expertise in at least two of the following programming languages: Python, JavaScript/TypeScript, or C#. Cloud Platform Experience : Experience deploying and managing systems on at least one of the major cloud platforms (AWS, GCP, or Azure), utilizing containerization and implementing robust observability tooling. Web Application and API Development : Proven experience building and deploying robust, high-throughput full stack solutions including backend services/APIs that integrate with AI models and orchestrate complex workflows. Vector Databases: Familiarity with vector databases and embedding models. Security Focus: Demonstrated experience designing secure systems capable of safely handling untrusted code execution or complex user-generated content. Soft Skills: Excellent communication, collaboration skills, and the ability to autonomously drive technical initiatives from initial prototype through to high-scale production. Nice to Have: Experience with AI Agent evaluation frameworks. Familiarity with scalable inference pipelines. Familiarity with open tool protocols (e.g., MCP, A2A), browser automation etc. Prior work in EdTech. Familiarity with AWS Bedrock and Strands Agents Why Work With Us? When you work with Cambium Assessment, you’ll be helping to design and build inspiring solutions that make a real impact on the online testing industry, as well as the educators and students we support. Our systems are highly scaled and mission critical serving over a third of all students in grades 3-8 in the United States. Our web applications are highly interactive and universally accessible. Our machine scoring methods are driven by artificial intelligence allowing computers to perform such complex operations as grading essay