Experience building software using Ruby and/or Python
Previous experience building and maintaining ETL pipelines and processes.
Previous experience with operational components of modern web applications including asynchronous job queues, daemonized services, and CI/CD pipelines.
Previous experience with open source.
Experience with multi-modal data, including formats like PDF, HTML, Word docs.
Also, general knowledge of tooling and transformer architecture around LLMs.
Responsibilities:
Contributing to the development of large-scale applications using multi modal data with LLMs.
Architect, optimize, and maintain pipelines for processing and analyzing various data, including PDF, HTML, and image formats.
You will collaborate with and mentor international teammates in a mostly text-based, asynchronous, remote-first team environment with occasional video calls and yearly conferences.
You will collaborate with the team on features, breaking them down into technical deliverables.
You’ll act as an important and communicative part of an engaged and spirited team, working with data scientists and product teams to integrate AI-driven solutions.