AI Data Engineer – Build Scalable AI Pipelines

About the role

As an AI Data Engineer at FactualIQ, you will design, build, and maintain the data infrastructure that powers our enterprise Decision Engine. You will work on high‑performance pipelines and databases that enable real‑time, AI‑driven decision making for Fortune‑1000 clients.

Key responsibilities

• Implement and operate data pipelines supporting hundreds of concurrent AI agent workflows.
• Design, tune, and manage relational (PostgreSQL, MySQL) and vector (Pinecone, Weaviate, Qdrant) databases.
• Develop semantic search capabilities, including embedding pipelines and hybrid search.
• Build ETL, batch, and incremental processing workflows for agent context management.
• Create data models for multi‑tenant, temporal, and versioned AI workflows.
• Implement data quality, drift detection, monitoring, and alerting systems.
• Develop multi‑level caching and feature‑engineering pipelines for low‑latency access.
• Ensure data governance through classification, PII handling, and audit logging.
• Participate in sprint planning, technical discussions, and documentation.

Required profile

• Bachelor’s degree in Computer Science, Data Engineering, Statistics, or related field, or equivalent experience.
• 4+ years of production data‑engineering experience building pipelines and database systems.
• Strong problem‑solving skills and ability to work collaboratively with senior engineers.

Required skills

• Python programming.
• Data‑processing libraries: Pandas, Polars, DuckDB.
• Relational databases: PostgreSQL, MySQL.
• Vector databases: Pinecone, Weaviate, Qdrant.
• Experience with ETL, batch processing, and incremental data updates.
• Knowledge of semantic search, embedding pipelines, and hybrid search techniques.
• Data quality, monitoring, and drift detection practices.
• Caching strategies and feature‑engineering pipelines.
• Data governance, PII detection, and audit‑logging concepts.