Job Opportunity
The main goal of this position is to develop and refine Retrieval-Augmented Generation (RAG) models for searching across large medical and scientific documents.
You will work on strategies for breaking down semantic chunks, improving the automated evaluation pipeline, and fine-tuning Large Language Models (LLMs) for textual RAG applications.
This role involves hands-on experimentation, model development, and backend engineering, with deployments to non-production environments and collaboration with DevOps teams for production deployment.
Strong communication and team collaboration are essential in this individual contributor position.
1. Semantic chunking techniques
2. LLM fine-tuning expertise
3. Automated evaluation pipeline improvement