Remote AI Data Integration Engineer — RAG & Data Masking

Computer Task; United States; On-site; USD 83,000 - 96,000; Part time

Job summary

CTG is seeking an AI Data Integration Engineer – RAG Platform for a remote engagement. The role centers on configuring platform connectors to ingest partner profiles, public data, and data into a RAG data store.

You will implement PII minimization and data masking workflows, including hashing, before ingestion. You will validate webhook and event flows, map data to canonical schemas, and route events to analytics stores.

Qualifications

• Hands-on experience configuring data connectors or ETL platforms.
• Experience integrating APIs, cloud storage, CRM systems, and data ingestion pipelines.
• Familiarity with RAG platforms and embedding-based ingestion workflows.

Responsibilities

• Configure platform connectors to ingest partner profiles, public data, and data into a RAG data store.
• Implement PII minimization and data masking workflows, including hashing, before ingestion.
• Validate webhook flows, map data to canonical schemas, and route events to analytics stores.
• Partner with Analytics teams to ensure data is queryable and analysis-ready.
• Maintain connector configurations, ingestion logs, event mappings, and masking audits.

Skills

ICA connectors

APIs integration

S3 connectors

CRM integrations

RAG ingestion

Data masking

PII minimization

Webhooks

Event mapping

Canonical schemas

Education

Bachelor’s degree in Computer Science, Information Technology, Data Engineering, or related field

Tools

ETL tools

Data integration platforms

HubSpot API

Salesforce API

Job description

CTG is seeking an AI Data Integration Engineer – RAG Platform for a remote engagement. The role centers on configuring platform connectors to ingest partner profiles, public data, and data into a RAG data store.

You will implement PII minimization and data masking workflows, including hashing, before ingestion. You will validate webhook and event flows, map data to canonical schemas, and route events to analytics stores.