Intel Multimodal Dialog Understanding Consultant in Santa Clara, California

Job Description

Visual and Embodied Dialog is a novel task that requires an AI agent to hold a meaningful dialog with humans in natural, conversational language about visual contents in the space around. To perform well on this task, the agent needs to ground the query not only in the visual content but also in the dialog history and build appropriate joint models of scene and dialog understanding.

This is a new area of Research in Multimodal Scene Understanding and Conversational Systems that brings together Researchers from Computer Vision, Dialog Systems and Deep Learning areas together to push the state of the art ahead in Visually Grounded Conversational Systems. In Anticipatory Computing Lab, we are conducting Research in Multimodal Sense-Making Areas to create compelling future AI and Intelligent Systems usages that require an assimilation of a variety of technologies such as Computer Vision, Audio Understanding and Language Understanding. This project helps bring together some of these technologies and fuse them appropriately to enable visual dialog capability on it.

To help us develop state of the art technologies in this area, we want to bring on-board a part time Summer Consultant from a reputed university. The hired candidate will work with researchers together to build models and prototypes on a suitable dataset for multimodal dialog understanding related area. The candidate should be a recognized expert in Multimodal Dialog Understanding area and should have published state of the art results at the top conferences related to Spoken Dialog Systems and Deep Learning areas.



· Help develop deep learning based models for interesting visual dialog understanding related problems.

· Provide consulting on state of the art models, practices and implementations for various multimodal architectures.

· Be able to actively take up module development responsibilities in the project.

Skills And Qualifications

· Expert knowledge of Deep Learning based Multimodal Architectures

· Proficient understanding of multimodal data collection systems

· Proficient knowledge of one or more of Deep Learning based Libraries (Tensorflow, Keras, PyTorch) for data processing and modeling requirements.

Inside this Business Group

Intel Labs is the company's world-class, industry leading research organization, responsible for driving Intel's technology pipeline and creating new opportunities. The mission of Intel Labs is to deliver breakthrough technologies to fuel Intel's growth. This includes identifying and exploring compelling new technologies and high risk opportunities ahead of business unit investment and demonstrating first-to-market technologies and innovative new usages for computing technology. Intel Labs engages the leading thinkers in academia and industry in addition to partnering closely with Intel business units.

Posting Statement. Intel prohibits discrimination based on race, color, religion, gender, national origin, age, disability, veteran status, marital status, pregnancy, gender expression or identity, sexual orientation or any other legally protected status.