AI Data Sensitivity Classification Developer

Relvix Data

Remote · $100k – $130k / year · Full-time · Posted 4 months ago

This role is no longer accepting applications

Don't miss the next role like this

Create a free profile with your skills. We match you to new AI roles as they open, and companies hiring can contact you directly.

Create free profile, 2 minutes

Similar open roles you can apply to now:

See all open AI jobs

This role is no longer accepting applications

Don't miss the next role like this

Create a free profile with your skills. We match you to new AI roles as they open, and companies hiring can contact you directly.

Create free profile, 2 minutes

Similar open roles you can apply to now:

See all open AI jobs

About the role

Most organizations don't know what sensitive data they have or where it is. Healthcare organizations with HIPAA obligations, financial institutions with PCI scope, and companies with GDPR personal data requirements all need to answer 'which tables contain which sensitivity classes of data' — and the answer changes constantly as new datasets are ingested and schemas evolve. Our data governance platform serves 65 enterprise clients managing compliance across complex data environments. Data sensitivity classification — automatically identifying and tagging columns containing PII, PHI, PCI data, or business-confidential information — is the foundational capability that everything else depends on. Our current classifier uses pattern matching and is embarrassingly wrong on anything beyond obvious patterns like SSNs and email addresses. You'll rebuild the sensitivity classification system with ML: training models that understand semantic column meaning from names, sample values, and table context, handling the long tail of sensitive data that looks nothing like a credit card number, and building the continuous classification pipeline that rescans as new tables arrive. The output feeds access control, masking policies, and retention management — getting it right has real compliance consequences.

Fully remote.

Responsibilities

Rebuild data sensitivity classifier using ML models trained on column names, sample values, and table context
Design training data collection strategy from client-consented labeled examples across sensitivity categories
Implement continuous classification pipeline rescanning new tables as they arrive in data catalogs
Build confidence scoring routing low-confidence classifications for human review
Create classification audit trail supporting compliance documentation requirements
Evaluate classifier accuracy against compliance team manual review benchmarks

Requirements

3+ years in data engineering, data governance, or ML for structured data
Strong Python, SQL, and Spark skills with data catalog or metadata management experience
Understanding of PII, PHI, PCI, and GDPR data sensitivity categories
Experience building classification systems for structured or semi-structured data
Familiarity with enterprise data compliance frameworks and requirements