Job Description

We’re looking for someone who is (or can quickly become) strong in end-to-end LLMOps: building and optimizing LLM pipelines, managing inference performance, improving reliability, and supporting production AI features. You’ll work closely with our Staff Engineer and Data Engineer on a small, highly technical team. We don’t have hard requirements around degrees or specific model frameworks - but you do need hands-on experience with LLMs, vector databases, embeddings, prompt optimization, and deploying/maintaining ML systems in production. Part of the process includes a practical take-home assignment (real-world, not leetcode), followed by technical conversations with engineering leadership. We’re looking for someone who can think in systems, make good architectural decisions, and operate with a high level of ownership. Thrive is not a place where work is micromanaged - you’ll thrive here (pun intended) if you’re proactive, self-directed, and comfortable moving quickly without rigid structure.