Vector Database Engineer

Description

We are seeking a Postgres Database Engineer with expertise in maintaining Postgres databases optimized for vector search using pgvector. You will manage performance, availability, backup, and DR for AI-driven enterprise workloads.

Responsibilities

• Maintain Postgres with pgvector extension for embeddings.
• Optimize vector similarity search queries at scale.
• Implement backups, restore, and DR drills.
• Monitor performance metrics and replication lag.
• Collaborate with AI/ML teams for retrieval optimization.

Qualifications

• Bachelors in Computer Science, Data Engineering, or related field.
• 4+ years DBA experience with Postgres.
• Skilled in query tuning, partitioning, indexing.
• Experience with pgBackRest/WAL-G.
• Familiarity with Postgres HA setups.

Required Skills

• Vector database design, deployment, and optimization.
• Familiarity with platforms: Milvus, Pinecone, Chroma, pgvector/PostgreSQL, MongoDB Atlas Vector Search.
• Advanced proficiency in Approximate Nearest Neighbor (ANN) algorithms, e.g., HNSW, IVF, PQ, and LSH, for low-latency vector search at scale
• Building and tuning hybrid indexes to support both vector similarity and metadata (structured) filtering in queries.
• Handling sub-100ms response times for high-throughput, real-time search and recommendation workloads
• Embedding generation and manipulation: Skilled at generating semantic embeddings using models like BERT, Word2Vec, Sentence-BERT, and integrating these with database workflows.
• Vector-aware sharding, data partitioning, and rebalancing strategies for scaling and resilience
• Storage optimization including vector quantization, sparse data representations, and time-based partitioning for hot/cold data separation.

Career Growth:

Pathway to Database Architect or Data Platform Specialist roles focused on enterprise-scale AI workloads.