Deeply understanding our product, and planning & showcasing where LLMs and future AI enhancement would best be placed to deliver actual value to our users.
Leading by doing – demonstrating best practices in prompt engineering, RAG implementation, and AI system architecture through hands-on development while mentoring the team through practical examples and code reviews.
Building and maintaining production-ready AI systems, including implementing monitoring solutions and setting up prompt evaluation frameworks.
Driving practical AI implementation decisions, from model selection and cost optimization to scaling solutions across our production environments.
Ensuring we keep our DORA metrics amongst the best in the industry so that we keep our time-to-ship low, and developer happiness high.
Working in a CI-backed environment, in small teams, in three-week cycles. We use Linear internally and follow their opinionated development process.
Requirements & Skills:
You have an AI-positive mindset and want to apply and build upon your learning with an existing product.
You either have commercial experience with using LLMs to enhance products, or you have been using them in your own time and want some real-world experience.
Have experience working on full-stack applications, in particular Python/TypeScript/React ones.
Have experience working with remote distributed teams, and the async communication and working patterns that come with that.
Have a good oral & written handling of English, to help with the above.
Are happier shipping features than debating tabs vs spaces.
Prefer to move quickly and iteratively, and believe that shipping incrementally and fast is best.
Are comfortable with Git, GitHub, and CI workflows.
Have experience with successfully deployed LLM projects, although we understand this is a new field
Have experience working with Django or other web applications, in particular Python ones.
