Generative AI Evaluation Clinical Scientist
Description For Generative AI Evaluation Clinical Scientist
Google Health is a company-wide effort to help billions of people be healthier. We work toward this vision by meeting people in their everyday moments and empowering them to stay healthy and partnering with care teams to provide more accurate, accessible, and equitable care. Our teams are applying our expertise and technology to improve health outcomes globally – with high-quality information and tools to help people manage their health and wellbeing, solutions to transform care delivery, research to catalyze the use of artificial intelligence for the screening and diagnosis of disease, and data and insights to the public health community.
As a Generative AI Evaluation Clinical Scientist, you will be responsible for developing, validating, and deploying standardized rating instruments to assess the quality, accuracy, robustness, and efficacy of AI models in health-related areas. You will design and execute evaluations of AI models, focusing on assessing information quality, clinical impact, safety, and potential biases. The role requires expertise in qualitative and quantitative research methods, including clinical study design and execution, to design state-of-the-art methods for AI model assessment.
You will collaborate closely with cross-functional teams, including engineers, clinicians, researchers, and product managers, to ensure that AI models are evaluated transparently throughout the development life-cycle. The position also requires programming skills (e.g., Python/Colab/Jupyter notebooks, R) to conduct analyses, develop evaluation tools, and support scaling of automated evaluation workflows.
This role offers an opportunity to work at the forefront of AI in healthcare, ensuring that Google's health initiatives align with the company's AI Principles, regulatory guidelines, and industry best practices. You will play a crucial role in assessing the potential impact and safety of AI models in healthcare, contributing to the development of more accurate, accessible, and equitable care solutions.
Responsibilities For Generative AI Evaluation Clinical Scientist
- Develop, validate, and deploy standardized rating instruments to assess the quality, accuracy, robustness, and efficacy of AI models, ensuring alignment with Google's AI Principles, regulatory guidelines, and industry best practices
- Design and execute evaluations of AI models in health-related areas, with a focus on assessing information quality, clinical impact, safety, and potential biases
- Employ expertise in qualitative and quantitative research methods, including clinical study design and execution, to design state-of-the-art methods for AI model assessment
- Collaborate closely with cross-functional teams, including engineers, clinicians, researchers, and product managers, to ensure that AI models are evaluated transparently throughout the development life-cycle
- Leverage programming skills (e.g., Python/Colab/Jupyter notebooks, R) to conduct analyses, develop evaluation tools, and support scaling of automated evaluation workflows
Requirements For Generative AI Evaluation Clinical Scientist
- Medical degree (e.g., MD, MBBS, or equivalent degree) or a PhD in Health Informatics, Psychology, Biomedical Engineering, Epidemiology or relevant field with formal research training
- 3 years of experience applying qualitative and quantitative research methods relevant to health AI model validation
- Experience implementing analysis with tools relevant to AI evaluation
