AI Data Engineer

Semantic Enterprise AI (SEAI) builds next-generation Decision Engine workflows that integrate machine learning, agentic automation, and advanced reasoning tools into enterprise products that empower organizations to make better upside decisions faster.

As an AI Data Engineer, you'll build and maintain the data infrastructure that powers SEAI's Decision Engine at enterprise scale. You'll implement data systems, build pipelines, and develop the data processing infrastructure that enables intelligent workflows for Fortune 1000 clients. This is a hands‑on technical role where you'll work alongside senior engineers to build reliable, performant data systems that support client‑critical AI decision‑making while growing your expertise in advanced data engineering for AI applications.

• Implement and maintain data pipelines that support hundreds of concurrent agent workflows with reliable performance for real‑time decision support.
• Build and optimize database systems including relational databases (Postgre
  
  SQL, MySQL), vector databases (Pinecone, Weaviate, Qdrant), implementing indexing strategies and query optimization patterns.
• Develop semantic search capabilities including embedding pipelines, hybrid search implementations combining vector and traditional search, and result ranking systems.
• Build data processing workflows for agent context management including ETL pipelines, batch processing systems, and incremental data update patterns.
• Implement data models for AI workflows including temporal patterns, multi‑tenant data structures, and schema versioning approaches.
• Develop data quality and monitoring systems including validation frameworks, data drift detection, pipeline health checks, and automated alerting.
• Build caching systems for semantic data including multi‑level cache implementations, cache invalidation logic, and performance optimization.
• Implement feature engineering pipelines including feature computation, versioning systems, and serving infrastructure for low‑latency access.
• Develop data governance components including data classification, PII detection and handling, and audit logging for compliance requirements.
• Optimize data system performance including query tuning, index design, and cost‑effective data storage strategies.
• Participate in sprint planning, contribute to technical discussions, and maintain clear documentation for data systems and processes.
• Stay current with emerging best practices in data engineering and AI data systems, incorporating learnings into your work.

• Bachelor's degree in Computer Science, Data Engineering, Statistics, or related technical field (or equivalent practical experience).
• 4+ years of production data engineering experience with hands‑on development of data pipelines, database systems, and data processing workflows.
• Strong Python proficiency with solid understanding of data processing libraries (Pandas, Polars, DuckDB) and performance considerations for data workloads.
• Production experience with relational databases (Postgre
  
  SQL, MySQL) including query optimization, index design, and understanding of scaling approaches.
• Experience with vector databases and semantic search (Pinecone, Weaviate, Qdrant, Chroma
  
  DB) including implementation of search systems and understanding of embedding‑based retrieval.
• Experience with data pipeline orchestration tools (Airflow, Prefect, Dagster) including workflow design and error handling patterns.
• Strong SQL skills including complex queries, window functions, CTEs, and ability to optimize query performance.
• Understanding of data modeling approaches including normalized schemas, dimensional modeling, and trade‑offs for different use cases.
• Experience with cloud data platforms (AWS RDS/Aurora, GCP Cloud SQL, Azure Database) and infrastructure provisioning.
• Familiarity with embedding models and semantic processing including model selection, chunking approaches, and quality evaluation.
• Experience building RAG (Retrieval Augmented Generation) systems including chunking strategies, context optimization, and retrieval patterns.
• Understanding of data quality practices including monitoring, validation,…