Profile cover
N

AI Synthetic Bias Injection Test Engineer

Noah Kovacs

Contract · Job · London

About the role

Our mission is to make AI systems provably fair before they reach production, not after a regulator or a lawsuit forces the question. Python, scikit-learn, and a custom perturbation framework are the tools you'll use daily to construct synthetic datasets with known, controlled bias patterns, then run them against client models to surface blind spots standard fairness metrics miss. This work directly shapes what our clients disclose in their model cards and audit reports — the edge cases you find become the test suite that catches the next generation of bias before it ships.

Responsibilities

  • Design synthetic datasets with controlled, known bias patterns
  • Run perturbation tests against client models and interpret results
  • Build reusable bias injection templates for common model types
  • Translate findings into audit-ready documentation
  • Collaborate with client ML teams on remediation approaches

Requirements

  • Background in statistics or applied ML with a focus on fairness
  • Experience with scikit-learn and Python for experimental pipelines
  • Understanding of common fairness metrics and their limitations
  • Comfortable writing findings for non-technical compliance audiences

Benefits

  • Fully remote
  • Contract with possibility of extension
  • Flexible hours across time zones
  • Access to internal fairness research library

Keep exploring related roles

Use these topic pages to discover more roles in the same hiring cluster.

Job Type

Contract

Level

Senior

Language

English

Salary Range

$130k – $160k / year

AI Expertise

AI & Machine Learning Engineers AI Business, Marketing & Strategy

Skills

python scikit-learn statistics r azure

Ready to apply for this role?

Create a free talent account in under 2 minutes.

  • Apply to verified AI companies
  • Get AI-matched job recommendations
  • Message hiring managers directly
  • Build your public AI talent profile

Interested in this role? Create your free profile to apply.

Apply — create free profile