Source description
About the role
We are hiring an experienced AI Data Engineer to build production-grade data infrastructure for enterprise AI applications. This role focuses on Retrieval-Augmented Generation (RAG), vector databases, embedding pipelines, OCR, and document intelligence solutions. Responsibilities Build scalable document ingestion pipelinesDevelop embedding and chunking pipelinesManage vector databasesBuild OCR and document processing workflowsDesign retrieval evaluation frameworksOptimize production RAG systemsWork with cloud-native AI infrastructureRequired Skills 810 years of Data Engineering experience2+ years building production LLM/RAG systemsPython (Pandas, PySpark, FastAPI)SQLPinecone, Weaviate, Milvus, Qdrant, pgvector or ChromaOpenAI Embeddings, Cohere, BGE, Sentence TransformersAirflow/Dagster/PrefectAWS Textract, Azure Document Intelligence, Google Document AI, Tesseract or PaddleOCRAWS/Azure/GCPPreferred Hybrid Search (BM25 + Dense Retrieval)Indic NLPPII DetectionKnowledge GraphsHealthcare/BFSI experiencePay: Up to 2,000,000.00 per year Experience: AI Data Engineer: 8 years (Required)Work Location: In person We are hiring an experienced AI Data Engineer to build production-grade data infrastructure for enterprise AI applications. This role focuses on Retrieval-Augmented Generation (RAG), vector databases, embedding pipelines, OCR, and document intelligence solutions. Responsibilities Build scalable document ingestion pipelinesDevelop embedding and chunking pipelinesManage vector databasesBuild OCR and document processing workflowsDesign retrieval evaluation frameworksOptimize production RAG systemsWork with cloud-native AI infrastructureRequired Skills 810 years of Data Engineering experience2+ years building production LLM/RAG systemsPython (Pandas, PySpark, FastAPI)SQLPinecone, Weaviate, Milvus, Qdrant, pgvector or ChromaOpenAI Embeddings, Cohere, BGE, Sentence TransformersAirflow/Dagster/PrefectAWS Textract, Azure Document Intelligence, Google Document AI, Tesseract or PaddleOCRAWS/Azure/GCPPreferred Hybrid Search (BM25 + Dense Retrieval)Indic NLPPII DetectionKnowledge GraphsHealthcare/BFSI experiencePay: Up to 2,000,000.00 per year Experience: AI Data Engineer: 8 years (Required)Work Location: In person
More at Hindustan Recruitment Services Pvt. Ltd.