Senior Software Engineer (AI Applications)

Accountabilities

• Design, build, and deploy advanced Generative AI agents with capabilities such as persistent memory, shared state management, and multi-step reasoning workflows.
• Arcitect and implement AI-enabled web applications that improve user experiences and deliver measurable product impact.
• Integrate large language models (LLMs) and multimodal AI technologies into existing platforms while ensuring performance, reliability, and safety.
• Develop evaluation frameworks for AI agents, including testing strategies, performance monitoring, and safety assessments.
• Build scalable backend services, APIs, and AI orchestration workflows supporting high-volume production environments.
• Partner with product, engineering, and research teams to translate user needs and complex workflows into production-ready AI capabilities.
• Establish best practices for secure AI development, responsible AI implementation, and trustworthy system behavior.
• Provide technical mentorship and guidance on AI architecture, LLM integration patterns, and autonomous system design.
• Drive technical initiatives from early prototypes through deployment and continuous improvement.

Requirements

• Strong software engineering expertise with hands-on experience building AI applications and agentic systems.
• 5+ years of software engineering experience, including 2+ years operating at a senior or staff level leading significant technical initiatives.
• Proven experience designing and building complex AI agent systems, including tool calling, prompt optimization, and context engineering.
• Advanced programming skills in at least two of the following languages: Python, JavaScript/TypeScript, or C#.
• Experience deploying and managing applications on major cloud platforms such as AWS, Google Cloud Platform, or Azure.
• Experience with containerization, observability tools, and production-scale software systems.
• Experience with large language models (LLMs), prompt engineering techniques, and Retrieval-Augmented Generation (RAG) pipelines.
• Experience with vector databases and embedding models.
• Experience designing secure systems capable of handling untrusted code execution or complex user-generated content.
• Strong communication and collaboration skills with the ability to independently drive technical projects.
• Experience with AI agent evaluation frameworks, scalable inference pipelines, open tool protocols, browser automation, or AI infrastructure is a plus.
• Prior experience in education technology is preferred.
• Familiarity with AWS Bedrock and Strands Agents is a plus.

Benefits

• Full remote work environment with flexibility to support work-life balance.
• Remote office setup reimbursement to support an effective home workspace.
• Opportunity to work on highly scaled, mission-critical technology serving millions of learners and educators.
• Collaborative environment focused on responsible AI development and meaningful impact.
• Inclusive workplace culture that values diverse backgrounds, ideas, and experiences.
• Supportive benefits package and employee resources.