Job Title: AI/LLM Developer
About the Role:
We are hiring a skilled AI/LLM developer to join a small team building backend features for a Retrieval-Augmented Generation (RAG) service.
Your primary focus will be building and optimizing RAG models for search across large-scale medical and scientific documents, including pre-processing and embedding over half a billion documents.
You'll work on semantic chunking strategies, improving the automated evaluation pipeline, and fine-tuning LLMs for textual RAG use cases.
The role involves hands-on experimentation, model development, and backend engineering, with deployments to non-prod environments and collaboration with DevOps for production rollout.
* Key Responsibilities:
* • Develop and optimize RAG models for search functionality
* • Implement semantic chunking strategies for improved accuracy
* • Enhance the automated evaluation pipeline for RAG models
* • Fine-tune LLMs for textual RAG use cases
Requirements:
To succeed in this role, you should have:
* • Proficiency in developing and deploying AI/LLM models
* • Strong understanding of natural language processing and generation techniques
* • Experience with cloud-based infrastructure and deployment tools
* • Excellent problem-solving skills and attention to detail
Benefits:
This is an excellent opportunity to work with a talented team, develop your skills, and contribute to cutting-edge projects. You'll have access to:
* • State-of-the-art infrastructure and tools
* • Opportunities for growth and professional development
* • Collaborative and dynamic work environment