Key Responsibilities
- Design and implement core components of an AI tutoring system, including prompt architectures, agentic workflows, and adaptive behaviors.
- Drive end-to-end experiments—shipping, measuring, and iterating to enhance learning outcomes and model performance.
- Develop production-grade systems integrating LLM capabilities into user-facing experiences with reliability, speed, and scalability.
- Translate product and pedagogical goals into technical solutions, collaborating with cross-functional teams.
- Prototype and deploy new model capabilities, bridging research breakthroughs with real user impact.
- Strengthen system quality through robust testing, monitoring, and iteration to ensure safe, consistent behavior at scale.
Requirements
- Proven experience building and shipping LLM-powered products in production environments.
- Strong prompt engineering skills and hands-on experience with agentic workflows or multi-step model interactions.
- Solid grasp of experimentation—designing, running, and interpreting experiments to drive improvements.
- Strong software engineering fundamentals (Python) with experience in scalable systems and modern production environments.
- Strong product instincts to connect model behavior with user experience and outcomes.