GenAI Data Engineer — Build Governed AI Pipelines

Cinteot Inc.; Newark (NJ); On-site; USD 120,000 - 170,000; Full time

Benefits offered by this job

Complete Insurance Coverage

401k with Company Contribution

Tuition Reimbursement

Generous Paid Time Off (birthday)

Job summary

Cinteot Inc. is seeking an AI Data Engineer to build and operate governed, AI-ready data pipelines powering GenAI and agent-based use cases.

This role emphasizes preparing data for retrieval-augmented generation, managing embeddings and vector indexes, and ensuring data quality, lineage, and compliance across the AI platform. As part of the AI CoE – Technology pod, you will collaborate with AI Platform Engineers and AI Engineers to support shared capabilities and priority AI use cases.

Qualifications

• Bachelor’s degree or equivalent in a related technical discipline.
• Experience designing/operating production-grade data pipelines in an enterprise.
• Experience with unstructured data (documents, PDFs) for analytics/AI use cases.
• Knowledge of embeddings, vector databases, and retrieval patterns in AI systems.
• Strong data quality, lineage, and governance understanding.

Responsibilities

• Design, build, and maintain data pipelines for AI use cases.
• Prepare RAG-ready datasets with metadata enrichment and document parsing patterns.
• Collaborate with source teams and SMEs to ensure accurate AI data representations.
• Create and maintain embedding pipelines and vector index maintenance.
• Ensure data governance, privacy, and regulatory compliance across AI pipelines.
• Monitor data freshness, quality, and usage trends to plan retirements or enhancements.

Skills

Data pipelines

Embeddings & vector databases

RAG readiness

Data governance

Cloud data services

Cross-functional collaboration

Education

Bachelor’s degree in CS/Engineering/Data Science

Tools

AWS

Azure

Databricks

Snowflake

Job description

Cinteot Inc. is seeking an AI Data Engineer to build and operate governed, AI-ready data pipelines powering GenAI and agent-based use cases.

This role emphasizes preparing data for retrieval-augmented generation, managing embeddings and vector indexes, and ensuring data quality, lineage, and compliance across the AI platform. As part of the AI CoE – Technology pod, you will collaborate with AI Platform Engineers and AI Engineers to support shared capabilities and priority AI use cases.