Deep Learning

  • Research
  • London, United Kingdom

Deep Learning

Job description

Synthesia is developing cutting-edge technology to edit and translate video content. We build AI technology that understands and models the intricacies of the human face, bringing entirely new capabilities to content creators.

 

Located in Angel, London we are a team of researchers from UCL, Stanford and Cambridge with experience in deep learning, visual effects and computer vision. We are passionate about making it easier to translate video content and make great stories travel the world.
 

Role

Our technology revolves around modelling, understanding and synthesising people in a way that is indistinguishable from normal video. We are looking for someone to take a key role in developing our deep learning capabilities for audio-visual analysis, making it possible to seamlessly translate video content between languages. You will be undertaking cutting edge research working with a world class team of researchers in direct collaboration with internationally leading academics in the field.


You will need a background in deep learning for computer vision and audio-visual content creation. You have an inquisitive nature with a clear track record experimenting with state-of-the-art techniques. You have strong experience in Python and deep learning frameworks (Tensorflow, PyTorch) as well as a keen interest in bringing these technologies to a production level cloud platform (AWS), solving real-world challenges backed by best-in-class data-sets.


This is an opportunity to join a proven start-up as the company scales. We are looking for someone that is passionate about solving complex problems, can take a creative approach to delivering requirements in a fast-paced environment and enjoys working in a highly collaborative team bringing cutting-edge technologies to market.


Our culture

We’re a young, visionary start-up working at the very forefront of computer vision research. Our core team has experience from world-class institutions in both industry and academia and we are determined to build a strong research-led company. We need curious people who are keen to learn and who can play a key role in growing the company and making sure the journey is a fun and memorable one.

Requirements

+ PhD involving deep learning for audio-visual analysis of people

+ Strong experience in Python and deep-learning frameworks (Tensorflow, PyTorch)

+ Track record in implementing state-of-the-art techniques in deep learning

+ Passionate about developing cutting-edge research and working in a startup