We are seeking an AI engineer to join a small, focused team working on backend features for a retrieval-augmented generation service. The primary focus will be building and optimizing models for search across large-scale medical and scientific documents.
The role involves hands-on experimentation with semantic chunking strategies, improving the automated evaluation pipeline, and fine-tuning LLMs for textual use cases.
Deployments will be made to non-prod environments and collaboration with DevOps for production rollout is expected. Effective communication and teamwork are essential.
You will work on tasks such as pre-processing and embedding large datasets, ensuring that documents are searchable and contextually accurate. This is a challenging but rewarding opportunity to make significant contributions to the development of this service.