RAG expert

We are seeking an experienced RAG (Retrieval-Augmented Generation) expert to help optimize and fine-tune the performance of our RAG platform. The successful candidate will play a key role in improving the efficiency and scalability of our platform, ensuring seamless functionality and robust performance.

This is a contractual position for a period of 1 month, with the possibility of extension based on performance and project needs. The ideal candidate will have a deep understanding of RAG models, expertise in LLM Monitoring tools, and prior experience working with the Milvus Vector Database. Familiarity with Azure Cloud will be considered a significant advantage.

Key Responsibilities:

• Optimize and fine-tune the performance of the existing RAG platform.
• Implement DevOps best practices to enhance platform efficiency, scalability, and reliability.
• Collaborate with the development team to ensure smooth integration and deployment pipelines.
• Work with Milvus Vector DB for vector database optimization and data handling.
• Monitor, troubleshoot, and resolve any issues related to platform performance.
• Ensure secure and scalable infrastructure using cloud technologies.

Preferred Qualifications:

• Proven experience in optimizing RAG platforms.
• Hands-on experience with Milvus Vector Database.
• Bonus: Familiarity with Azure Cloud services and infrastructure

Add screening questions also

• Do you have previous working experience on any Vector Database (required)
• Do you have any working experience with Milvus Vector DB (optional)
• Do you know how to use LangChain in LLM (required)
• Do you have any experience with LLM Monitoring tools (optional)