AI Data Engineer – Vector Database & RAG

We are hiring for AI Data Engineer – Vector Database & RAG if you are interested, please feel free to share your CV to SyedaRashna@lancesoft.com

Title: AI Data Engineer – Vector Database & RAG

Location: Offshore India- Bangalore

Duration: 6 Months

Description:

The role will be responsible for designing, building, governing, and operating the enterprise vector database platform used across AI and GenAI use cases.

The candidate must combine:

• Hands-on vector database expertise preferably Oracle 26 AI / Milvus or any other vector database.
• Production experience building RAG solutions
• Strong data engineering fundamentals
• Understanding of AI data governance, security, lineage, and operational controls
• Ability to establish a new capability from the ground upKey Responsibilities
• Design and manage vector database architecture and retrieval services.
• Build end-to-end RAG pipelines including ingestion, chunking, embedding, indexing, and retrieval.
• Develop scalable data pipelines for structured and unstructured data.
• Implement data quality, metadata, lineage, security, and access controls.
• Optimize retrieval accuracy, performance, scalability, and operational monitoring.
• Establish governance and reusable standards for enterprise AI use cases.Required Skills & Experience
• Hands-on experience with Vector Databases (e.g., Milvus, Oracle AI Vector Search, Pinecone, Weaviate, Qdrant, pgVector).
• Proven experience delivering production-grade RAG solutions.
• Strong Python, SQL, and Data Engineering expertise.
• Knowledge of embeddings, semantic search, hybrid search, reranking, and LLM integration.
• Experience with APIs, CI/CD, containers, and cloud/on-prem platforms.
• Understanding of data governance, security, lineage, and audit requirements.Preferred
• Experience in banking or regulated industries.
• Familiarity with LangChain, LlamaIndex, Databricks, Spark, Kafka, or Airflow.
• Experience building enterprise-scale AI platforms from the ground up.Experience
• 8+ years of total Experiance in Data & AI with 4+ years working on AI/ML data platforms, semantic search, vector databases, or GenAI solutions and 2+ years of hands-on experience designing and deploying production-grade RAG solutions.