Senior Vector DB Engineer

Role : Senior Vector Database Engineer

Experience : 5+ years

Location : [Pune or Remote]

About The Role

We are seeking an experienced Vector Database Engineer to design, optimize, and maintain large-scale vector storage and retrieval systems. The ideal candidate will have a strong background in database internals, embeddings, and AI / ML data infrastructure.

Key Responsibilities

Design and implement high-performance vector storage, indexing, and retrieval systems for AI / LLM workloads.

Integrate vector databases (e.g., Pinecone, Milvus, Weaviate, FAISS, Chroma) into production pipelines.

Optimize data ingestion, indexing, and query performance for large-scale embeddings.

Collaborate with data scientists and ML engineers to support semantic search and RAG (Retrieval-Augmented Generation) use cases.

Ensure data reliability, scalability, and security across deployments.

Automate database management, scaling, and backup procedures.

Must-Have Skills

Strong programming skills in Python, Go, or Java.

Hands-on experience with vector databases (Pinecone, Milvus, Weaviate, Chroma, FAISS, or similar).

Understanding of embeddings, ANN (Approximate Nearest Neighbor) search, and similarity algorithms.

Experience with NoSQL and distributed databases (Elasticsearch, Cassandra, MongoDB, etc.).

Familiarity with cloud platforms (AWS, GCP, or Azure) and containerization (Docker, Kubernetes).

Good to Have

Exposure to LLM pipelines, RAG architecture, or knowledge graph systems.

Experience with MLOps or data infrastructure for AI systems.

Knowledge of LangChain, LlamaIndex, or OpenAI API integration.

Vector Database,Rag

Skills Required

Java, Cassandra, Go, Nosql, Gcp, Docker, Elasticsearch, Mongodb, Azure, Kubernetes, Python, Aws