ML Researcher, Fairness & Evaluation

About the Role

You will define how we measure our models and make sure they perform evenly across demographics. Your benchmarks decide what ships.

What You'll Do

• Design evaluation protocols and fairness metrics for every model release
• Find and fix accuracy gaps across demographic groups
• Set match thresholds and calibrate confidence scores
• Publish internal reports that guide model and product decisions

What You Bring

• PhD or equivalent research experience in ML or computer vision
• Strong statistics and experiment design
• Experience with bias measurement in vision or biometric systems
• Clear writing for technical and non-technical readers

Nice to Have

• Familiarity with NIST FRVT style evaluations
• Experience with synthetic data for evaluation