AI Research Scientist, Computer Vision - GenAI Evaluations
Meta

We are looking to hire an experienced Research Scientist to help us measure multimodal capability of GenAI models. The ideal candidate is knowledgeable about how to use evaluations and datasets to allow us to evaluate our models for images and video. This involves researching existing benchmarks available as well as coming up with novel approaches to evaluate our GenAI models.

AI Research Scientist, Computer Vision - GenAI Evaluations Responsibilities:

• Design and implement methods to evaluate our LLMs on multimodal capabilities.
• Adapt standard eval methods to best exploit modern parallel environments (e.g. distributed clusters, multicore SMP, and GPU).
• Work with a large and globally distributed team across multiple functions to understand the needs and align on goals and outcomes.
• Contribute to publications and open-sourcing efforts.
• Play a significant role in healthy cross-functional collaboration.

Minimum Qualifications:

• Bachelor's degree in Computer Science, Computer Engineering, relevant technical field, or equivalent practical experience.
• PhD in Computer Science, Computer Engineering, relevant technical field
• 5+ year(s) of work experience in a university, industry, or government lab with emphasis on AI Research in machine learning, vision and deep learning
• Programming experience in Python and hands-on experience with frameworks such as PyTorch.
• Exposure to architectural patterns of large scale software applications.
• Domain-Relevant Research Publications accepted at peer-reviewed AI conferences (e.g., NeurIPS, CVPR, ICML, ICLR, ICCV, and ACL)

Preferred Qualifications:

• First author publications at peer-reviewed AI conferences (e.g., NeurIPS, CVPR, ICML, ICLR, ICCV, and ACL).
• Direct experience in building evals for generative AI and LLM research

About Meta: