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 pipelines
- Develop embedding and chunking pipelines
- Manage vector databases
- Build OCR and document processing workflows
- Design retrieval evaluation frameworks
- Optimize production RAG systems
- Work with cloud-native AI infrastructure
Required Skills
- 8–10 years of Data Engineering experience
- 2+ years building production LLM/RAG systems
- Python (Pandas, PySpark, FastAPI)
- SQL
- Pinecone, Weaviate, Milvus, Qdrant, pgvector or Chroma
- OpenAI Embeddings, Cohere, BGE, Sentence Transformers
- Airflow/Dagster/Prefect
- AWS Textract, Azure Document Intelligence, Google Document AI, Tesseract or PaddleOCR
- AWS/Azure/GCP
Preferred
- Hybrid Search (BM25 + Dense Retrieval)
- Indic NLP
- PII Detection
- Knowledge Graphs
- Healthcare/BFSI experience
Pay: Up to ₹2,000,000.00 per year
Experience:
- AI Data Engineer: 8 years (Required)
Work Location: In person
