Description
DS Group have partnered with a company which is the global leader in synthetic media. Their vision is to build the first fully programmable video generation platform and help everyone transform non-video content into video.
They are already working with some of the world’s biggest companies and celebrities such as David Beckham and Lionel Messi, BBC, EY, Facebook, McDonalds, Amazon and WPP.
Their Messi campaign collaboration received a Cannes Lion Award in 2021 and they’ve raised more than $66M so far from names like Marc Cuban, First Mark Capital, Seedcamp, Google Ventures, Kleiner Perkins and more.
About the Position
This company are pioneering the field of synthetic media and are looking for a Language Engineer to join the team to help make synthetic humans look and sound exactly like a real person in video. In this position, you'll be working to help them connect text-to-video. They give users the ability to create video on demand with synthetic humans simply by writing and directing the script. You will be a central part of a small dynamic team that helps connect the script to the final audio-visual performance that we generate.
The company are very proud of their research culture and the impact they have achieved in visual synthesis of digital humans with their AI Avatars. You'll have the opportunity to work with multiple R&D teams across diverse areas in direct collaboration with internationally leading academics. As they scale you'll become a fundamental part of how the future of synthetic media is shaped.
Responsibilities
Build their end-to-end pipeline for textual data acquisition
Automate their data ingestion and annotation processes
Unify natural language processing across languages
Build and deliver multi-lingual data-sets
Deliver phonemic transcriptions
Build a pipeline for phonemization of data-sets
Develop rules for text normalization
Develop methods to extract linguistic structure and semantics
Improve natural language understanding in audio/video synthesis
Define how they test and evaluate quality for synthetic media
Requirements
BA in Linguistics
MSc in Computational Linguistics and Speech Processing
Native-level speaker of English
Strong understanding of multi-lingual phonetics
Practical experience in transcribing, annotating and analyzing speech
Theoretical and practical experience with NLP, ASR, TTS, machine translation
Experienced in machine learning (PyTorch) and software development (Python)
Excellent verbal and written communication skills
In short: You have a passion for computational linguistics, you care about the detail, you take pride in what you deliver and you want to have an impact. This is an exciting opportunity to join a world-class research team building a completely new category of technology.
Benefits
Stock Option Plan
Flexible Work From Home Policy
Very competitive compensation
Great office location in the heart of Soho (London)
Annual company retreats
Why now is a really exciting time to join this company?
The company is the world’s leader in synthetic AI video generation working with some of the world’s biggest corporate and media brands
They have crazy user traction with our first self-service product for businesses in just a year since the unveiling
They have a very high NPS of 71 and growing
They are launching new super exciting products in 2022
🚀 They are still a small team of 80 people and are growing fast! Join the rocketship while it's taking off.