Research Engineer (Audio-Visual Learning) - US
Location: Santa Monica
Posted on: January 16, 2022
Are you a hands-on Computer Vision and Audio Scientist with a
solid background in Machine Learning who loves solving challenging
real-world audio-visual learning problems and is eager to design
solutions that will help us revolutionize content creation for
films and TV?
Do you want to help revolutionize the way that Film and TV are
experienced across the globe? Do you dream of working with the
world's best Technologists, Visual Effects Editors, and AI
Scientists? Then look no further...We Are Flawless!
Here at Flawless, our first AI-based technology can visually
translate a film or TV show into any language whilst preserving the
original actor's performances, so you can enjoy it without annoying
subtitles or poor dubbing! Our recent launch has attracted interest
from several global streaming services & film studios, cementing
our position as pioneers in a multi-billion dollar industry.
To take full advantage of this position, we are expanding our
Research team in LA with multiple Research Engineers to contribute
to novel AI-based audio technology deployed at scale to turn
science into unique business products.
To succeed, you should have:
- Demonstrable 3+ years research experience (academic or
industry) with Computer Vision, Signal Processing, and Deep
Learning in at least four of the following:
- Neural networks and transfer learning
- Generative/adversarial models esp. for visual speech
- Multi-modal fusion and cross-domain adaption techniques for
- Recurrent and visual attention models for audio-video
- Audio-driven face animation
- Speech modeling and synthesis esp. with deep networks
- Statistical sgnal processing techniques mainly for audio
- Scholarly work in computer vision, signal processing, and
machine learning venues.
- Good background in statistical methods and numerical
- Excellent coding skills in Python
- Proficiency with DL frameworks such as PyTorch, Tensorflow, or
- Good communication skills to collaborate in a team with
researchers, ML engineers, and VFX artists
- MS or Ph.D. in Computer Vision, Speech Recognition and
Synthesis, Machine Learning, or related fields
Youll shine if you have experience with:
- Multi-modal audio separation
- Developing tools or solutions at scale for multi-modal or
audio-driven visual systems in AR/VR or VFX
- C++ and CUDA
- Cloud platforms such as GCP and AWS
- Virtual environments such as Anaconda
- Audio and post-production tools such as Avid, Resolve, or After
What you'll get from us:
- Autonomy - you own the work that you do from start to finish,
and you'll have the opportunity to influence research ideas and
independently implement and evaluate them in modern deep learning
and company tech stack at scale.
- Career growth in science - youll be up to speed with major
scientific advances, contribute ideas to scholarly articles and
patents, and participate at major conferences in AI-related
- Learning & development - you'll be working with the world's
best Technologists, Visual Effects Editors & AI Scientists to push
the boundaries of what is possible.
- Inclusive culture - collaboration is essential, everyone's
opinion and input are genuinely valued.
- Be part of something BIG - we are changing the Film & TV
industry for the better, breaking down language barriers, and
bringing people closer together.
Working for Flawless:
- Enjoy our flexible working environment and hybrid office
- Benefit from our shared success - all new joiners are given
- Competitive salary (ignore Glassdoor/Indeed estimate)
- Celebrate together - work across teams to solve challenging
problems and push the boundaries of video content creation.
- Networking in the film industry
- Medical / dental / vision insurance
- Basic 401(k) plan
- Corporate laptop
Apply today and help us shape the future of Film & TV.by
Keywords: Flawless, Santa Monica , Research Engineer (Audio-Visual Learning) - US, Engineering , Santa Monica, California
Didn't find what you're looking for? Search again!