2 months ago
Responsibilities
- Build and evolve the core AI tutoring system, including prompt architectures, agentic workflows, and real-time adaptive behaviors.
- Run experimentation and evaluation using custom metrics and frameworks to measure learning effectiveness and model reliability.
- Design and implement scalable software integrating AI capabilities with platform systems, content pipelines, and user experience components.
- Collaborate with educators, content creators, and product teams to translate pedagogical goals into technical solutions.
- Prototype and productionize novel model interactions using emerging AI research and capabilities.
- Improve quality, safety, and observability through monitoring, testing, guardrails, and iterative refinement.
- Share knowledge and elevate teammates through mentoring and collaboration.
Requirements
- At least 1 year of experience building complex LLM-based systems, including prompt engineering and agentic workflows.
- Ability to design meaningful evaluations, custom metrics, and evaluation frameworks.
- Strong software engineering fundamentals, architectural thinking, and fluency in Python.
- Experience or comfort with production infrastructure, cloud environments, and CI/CD.
- Ability to translate pedagogical goals into system behavior and product decisions.
- Ability to reason across AI behavior, content structure, platform features, and user experience.
- Familiarity with learning science or willingness to develop expertise.
- Strong communication, collaboration, mentoring, ownership, and problem-solving skills.
- Interest in AI research and emerging capabilities, with the ability to apply new ideas to practical problems.
Benefits
- Flexible working hours and remote work from the United Kingdom, Belgium, Portugal, or UAE.
- Yearly learning budget for conferences and training.
- International company retreats.
- Yearly IT equipment budget refresh for a home working setup.