Job Overview
We are seeking an AI/LLM Engineer to join a focused team developing backend features for a Retrieval-Augmented Generation (RAG) service.
* Design and optimize RAG models for efficient search across vast medical and scientific databases.
* Develop and embed over half a billion documents to ensure seamless searchability and contextual accuracy.
* Enhance the automated evaluation pipeline and fine-tune LLMs for textual RAG applications.
Required Expertise
* 1+ year of experience in Search Engineering or AI Development
* Proficiency in OpenSearch and building scalable search systems
* Strong Python development skills, including API creation, model training, testing, and general backend programming
* Familiarity with LangChain for building LLM workflows using tools, memory, and retrieval
* Excellent communication skills – able to work independently and provide clear updates to the team
Work Details
Location: Itaquaquecetuba, SP – Fully Remote
Contract Type: 10-month extending contract
Compensation: Paid on a monthly basis
Working Hours: 10AM - 6PM BRT (9AM-5PM EST)