Staff AI Engineer

Staff AI Engineer USA (Remote) with 20% Travel. At Robots & Pencils, we build meaningful, scalable digital products that solve real business problems. We're looking for a Staff AI Engineer to support the development and delivery of complex, integration-heavy platforms. This role is ideal for an experienced engineer who thrives in hands-on development, can confidently own features and deployments, and contributes to team leadership within a pod. In this role, you will work as a key contributor on a cross-functional team, building across the stack while helping guide delivery, improve systems, and solve challenging integration problems, including AI-native platforms such as agentic learning systems designed to enable human-centered learning in the Age of AI. This is not a greenfield project. You'll be joining a mature, production environment with real users, where reliability, performance, and scalability are critical. You'll collaborate closely with senior engineers to enhance existing systems and deliver high-quality features. By joining us, you leverage our Advanced AWS Partnership and the highly exclusive AWS Patterns Partnership, a distinction held by only 11 companies worldwide out of 190,000. What You'll Do Development • Build and maintain backend services using Python and Node.js, including serverless architectures (e.g., AWS Lambda, API Gateway) • Develop and integrate APIs that support frontend applications and external systems • Contribute to frontend features and ensure smooth integration across the stack • Write clean, maintainable, and well-tested code with strong unit testing practices Workflow & System Orchestration • Support the development and maintenance of workflows using orchestration tools (e.g., Sequencer / workflow engines, state machines) • Contribute to event-driven processes and asynchronous system operations (e.g., SQS,EventBridge) • Assist in improving reliability through better error handling and retries Backend & API Engineering • Develop RESTful APIs and support the BE architecture • Integrate with third-party services and internal systems, including AI-driven platforms • Assist in optimizing performance and scalability of services using DynamoDB single-table design patterns (composite keys, transactional writes) • Implement secure and reliable data handling practices System Reliability & Support • Troubleshoot issues in production environments with guidance from senior team members • Contribute to logging, monitoring, and debugging efforts • Support deployment and release processes in cloud-native environments (AWS, Docker) Collaboration & Growth • Work closely with cross-functional teams across global locations • Participate in code reviews and team discussions • Take ownership of assigned features and tasks, delivering end-to-end solutions • Continue developing technical skills and leveraging AI-assisted development tools (e.g., Claude Code) Required Skills & Experience • 6+years of professional software engineering • Strong experience with Python and Node.js • Experience with LLM function/tool calling, prompt engineering, multi-agent orchestration, vector databases (OpenSearch), embeddings, streaming LLM responses, RAG concepts. • Experience working with AWS cloud environments, including Lambda, DynamoDB (and Single-Table design), S3, SQS, EventBridge, Step Functions, etc. • Experience building and maintaining fullstack applications • Exposure to workflow orchestration tools (e.g., Sequencer or similar systems) • Solid understanding of API design and backend systems • Familiarity with databases (SQL and/or NoSQL, including scalable design patterns) • Experience working in production environments • Strong unit testing practices and maintainable test strategies • Experience with containerization (e.g., Docker) Nice to Have • Demonstrated ability to reason about system-wide impacts of changes, including downstream effects across services and data layers. • Demonstrated ability to identify design gaps in requirements and raise them before they reach development. • Experience with Langfuse, synthetic AI testing, token cost optimization, reasoning effort configuration, Step Functions for AI workflows.