Vector Data Engineer Brampton, ON, Canada (Onsite)

Job Title: Vector Data Engineer Location: Brampton, ON, Canada (Onsite) Experience: 5–7 Years Contract: 12 Months plus Notice Period: Immediate – 30 Days Please share the resume with me at [email protected] Short Job Description to Share with Candidates We are hiring an Vector Data Engineer with strong experience in building ETL pipelines, distributed data systems, and vector databases for AI/RAG applications. The ideal candidate should have hands-on expertise in structured & unstructured data processing, real-time data pipelines, search infrastructure, and data governance. Mandatory Skills 5–7 years of Data Engineering experience Strong experience in ETL development and Data Modeling Experience with SQL and distributed data systems Hands-on experience with Kafka, Spark, or Flink Experience with pgvector, Azure AI Search, and Redis Vector Database Knowledge of Vector Search, Hybrid Search, and BM25 Experience with semantic chunking, embedding models, and metadata tagging Real-time event-driven pipeline development for RAG/AI applications Data governance, Zero Trust, privacy, compliance, and auditability Database performance tuning and optimization Data quality, schema validation, and lineage tools (Great Expectations, OpenLineage) Experience with structured & unstructured data processing Preferred Skills Experience with Google GECX Exposure to LLMs, RAG, AI Agents, or Generative AI platforms

Build ETL pipelines, distributed data systems, and vector databases specifically for AI and RAG applications. Develop real-time event-driven pipelines while ensuring data governance, privacy, and compliance.

Requires 5-7 years of data engineering experience with expertise in SQL, Kafka, Spark, and vector databases like pgvector. Candidates should be proficient in semantic chunking, embedding models, and database performance tuning.

• SQLPreferred

Identified from the job description. Confirm important requirements above.

• Etl Development
• Data Modeling
• Sql
• Distributed Data Systems
• Kafka
• Spark
• Flink
• Pgvector
• Azure Ai Search
• Redis Vector Database
• Vector Search
• Hybrid Search
• Bm25
• Semantic Chunking
• Embedding Models
• Metadata Tagging

• Data & Analytics
• Technology
• Software
• Engineering

Minimum experience

5+ years

Apply by

Sep 5, 2026

Posting language

English

Working hours

40 hours per week

Seniority

Mid-Senior level

Application method

Direct apply is available