Job Description
We are looking for a Senior AI Data Engineer to build and scale the data infrastructure powering our AI products. In this role, you'll design robust document ingestion pipelines, vector databases, embedding workflows, and retrieval systems that enable high-performing RAG (Retrieval-Augmented Generation) applications across BFSI, Healthcare, Manufacturing, and Retail domains.
This is an AI-focused engineering role—not a traditional data warehousing or BI position. You'll work on OCR, multilingual NLP, vector search, and production-grade AI data pipelines that support enterprise LLM applications.
Key Responsibilities
- Design and build scalable document ingestion pipelines for enterprise data sources.
- Develop embedding, chunking, indexing, and vector search workflows for RAG applications.
- Implement and manage vector databases such as Pinecone, Weaviate, Qdrant, Milvus, pgvector, or Chroma.
- Build data services using Python, PySpark, SQL, and FastAPI.
- Develop OCR and document processing pipelines for scanned PDFs, forms, and semi-structured documents.
- Orchestrate data workflows using Airflow, Dagster, Prefect, or similar tools.
- Optimize retrieval quality through evaluation, monitoring, and performance tuning.
- Work with cloud platforms (AWS, Azure, or GCP) for scalable AI infrastructure.
- Collaborate with AI engineers, backend developers, and product teams to deliver production-ready AI solutions.
- Ensure data quality, security, and compliance with enterprise standards.
Required Skills & Qualifications
- 8–10 years of experience in Data Engineering, including 2+ years building production LLM/RAG data infrastructure.
- Strong proficiency in Python (Pandas, PySpark, FastAPI) and SQL.
- Hands-on experience with at least two vector databases (Pinecone, Weaviate, Qdrant, Milvus, pgvector, or Chroma).
- Experience with embedding models such as OpenAI Embeddings, Cohere, BGE, or Sentence Transformers.
- Experience with workflow orchestration tools like Airflow, Dagster, or Prefect.
- Hands-on experience with OCR/document AI tools such as AWS Textract, Azure Document Intelligence, Google Document AI, Tesseract, PaddleOCR, or Unstructured.io.
- Experience working with AWS, Azure, or GCP.
- Strong understanding of retrieval evaluation and RAG performance optimization.
Preferred Skills
- Experience with multilingual NLP, Indic languages, Hinglish, IndicBERT, IndicTrans, or AI4Bharat models.
- Knowledge of hybrid search (BM25 + Dense Retrieval) and reranking techniques.
- Experience with PII detection and masking tools such as Presidio or AWS Comprehend PII.
- Knowledge of knowledge graphs (Neo4j, ArangoDB) and Graph RAG.
- Understanding of DPDP Act 2023, HIPAA, or other data privacy regulations.
- Consulting or client-facing project delivery experience.
Why Join Us?
- Build production-grade AI systems solving real enterprise problems.
- Work on cutting-edge GenAI, RAG, vector search, and multilingual AI technologies.
- Collaborate with a high-performing engineering team.
- Hybrid work environment with opportunities for growth and ownership.
Job Type: Full-time
Location: Noida (Hybrid)
Experience: 8–10 Years
CTC: ₹15–20 LPA
Pay: ₹1,500,000.00 - ₹2,000,000.00 per year
Work Location: In person
