**Job Description**
The role involves joining a multidisciplinary team on an eBay-funded research project to develop a framework supporting vision-language (V-L) research. This framework will leverage existing pre-trained V-L models to enhance performance in tasks such as matching listings with products, product listing moderation, attribute extraction, and explained relevance prediction. It also has potential future applications as a testbed for customer support chatbots with image understanding and image-based product search.
**Skills & Abilities**
• Strong background in at least two of the following areas: machine learning, natural language processing, large language models, and multimodal processing
• Excellent programming skills
• Ability to work both independently and as part of a collaborative team, often across disciplines
• Experience with scientific writing and the preparation of research outputs
**Qualifications**
Required Degree(s) in:
• Computer Science
**Experience**
Other:
• At least a MSc in computer science
• Very good understanding of how visual language models work and can be used in practical applications
Note: We’ve analyzed the actual job post using AI, for more details visit the original job post by clicking on “Apply Now”!
