Post-doctoral Position in Explainable AI and Visualization
The Visualization, Imaging and Data Analysis (VIDA) Center has an opening for a post-doctoral associate to conduct innovative and exciting research in the area of explainability and visualization for machine learning. The project is in collaboration with Capital One and it aims at developing novel methods and systems to support model understanding and validation.
The position is available immediately but the start date is flexible.
- PhD in computer science or a related technical field
- Demonstrated ability to work independently and collaboratively in a diverse interdisciplinary team, and contribute to an active intellectual environment
- Excellent written and oral communication.
- Proficiency and experience in programming for machine learning and/or interactive data visualization systems
Expertise in one or more of the following areas is highly desirable:
- Deep learning
- Visualization and interactive user interfaces
- Statistics/probability and machine learning
- Empirical evaluation with user studies
The candidate is expected to:
- Perform excellent scientific research
- Develop research prototypes and conduct on-line and off-line evaluation
- Present results in top-tier international conferences
- Help in guiding PhD and Master students
- Participate in the VIDA activities
About New York University (NYU) and VIDA:
NYU is located in the heart of New York City and is one of the top private universities in the United States. VIDA is located at the NYU Tandon School of Engineering in downtown Brooklyn in the Brooklyn Tech Triangle, one of the most vibrant areas in the city for high-tech industry and education.
VIDA is an interdisciplinary center with strengths in big data and data science methods, including data management, visualization, machine learning, and in several application areas such as social sciences, neural science, medicine, biology, and physics.
The postdoctoral associate will join a dynamic group of undergraduate and graduate students, faculty members and industry partners to develop cutting edge research on machine learning visualization and interpretability.