Data Engineer
turbohire
Job Description
Build and maintain data ingestion pipelines (SharePoint, APIs, Blob storage)
•
Integrate AI/ML services (LLMs, embeddings, vector databases)
•
Implement and manage secure authentication and authorization mechanisms
•
Configure and use Azure Service Principals for secure service-to-service communication
•
Work with API gateways and secrets management systems (Key Vault)
•
Optimize document processing workflows (OCR, parsing, indexing)
•
Develop and maintain RAG pipelines (retrieval + response generation)
•
Handle duplicate detection, document filtering, and metadata tagging
•
Monitor system performance and ensure reliability with minimal downtime
•
Collaborate with cross-functional teams (AI, frontend, product)