Postdoctoral researcher position in vision-language processing

Computing Research Association; Abu Dhabi; On-site; AED 120,000 - 180,000; Full time

Job summary

A leading research institution is offering a 1-year postdoc position in vision-language processing located in Masdar City, Abu Dhabi. The role requires a PhD holder with extensive experience in vision-language models and a strong publication record. This position offers opportunities to work on innovative projects addressing scientific figure understanding and multimodal question answering.

Qualifications

• Strong publication record.
• Extensive experience with vision-language models.
• Must hold a PhD.

Responsibilities

• Focus on improved grounding and robustness of generative vision-language models.
• Conduct relevant tasks in scientific figure understanding and multimodal QA.

Skills

Scientific figure understanding

Text-in-image reasoning

Multimodal QA

Education

PhD in relevant field

Tools

VLMs (e.g., BLIP, LLaVA, Qwen)

Job description

Postdoc position @MBZUAI in vision-language processing, focusing on improved grounding and robustness of generative vision-language models.

Relevant tasks include scientific figure understanding, text-in-image reasoning, and multimodal QA.

Duration: 1-year in person position with the possibility of extension depending on satisfactory performance.

Location: Masdar City, Abu Dhabi, UAE.

Qualifications: Applicants should hold a PhD in a relevant field, have a strong publication record, and extensive experience with VLMs (e.g., BLIP, LLaVA, Qwen).

To apply, email your CV, cover letter, and contacts of at least two references to [e-mail] and [e-mail].

To access the full job description follow the link below:

https://docs.google.com/document/d/18fknVW-aOn6CrxDP_kP2KO1niKzIZE_ydb-29KFNhIw/edit?usp=sharing