Key Responsibilities

• Design and implement evaluation frameworks for AI model safety and performance
• Build automated test suites to detect model risks, bias, and failure modes
• Collaborate with data science and engineering teams to define evaluation metrics
• Document findings and recommend mitigations for identified risks
• Partner with cross-functional stakeholders on responsible AI practices

Requirements

• Life Sciences industry experience or prior experience at Johnson & Johnson (J&J) required
• Strong background in AI/ML model evaluation or AI safety
• Proficiency in Python and ML evaluation tooling
• Experience working with LLMs and evaluation pipelines
• Excellent communication skills for remote collaboration

Skills Required