Research Engineer - Audio Driven Facial Animation at Flawless

Santa Monica, California, United States

Apply Now

$175,000 – $210,000Compensation

Senior (5 to 8 years)Experience Level

Full TimeJob Type

UnknownVisa

Artificial Intelligence, EntertainmentIndustries

Requirements

Ph.D. or Postdoctoral researcher in 3D Computer Vision, Speech Synthesis, Computer Graphics, or related field
6+ years of experience in Python with proficiency in deep learning frameworks such as PyTorch or TensorFlow
Demonstrable research experience with a strong publication record in major 3D Computer Vision, Speech Processing, and Computer Graphics venues and journals (e.g., CVPR, SIGGRAPH, NeurIPS)
High degree of proficiency in math and statistical methods for signal processing
Experience with audio-visual learning, multimodal fusion, and/or 3D audio-driven face animation
Experience with speech modeling and speech synthesis with deep neural networks
Generative and cross-domain attention models for 3D visual speech synthesis applications
Outstanding communication skills for collaboration with scientists, research/ML engineers, and VFX artists

Responsibilities

Work with and lead a close-knit, passionate group of world-class individuals tackling challenging problems in deep learning
Focus on audio-driven 3D facial animation
Focus on GAN models for visual speech synthesis
Focus on speech-based modeling
Focus on multi-modal fusion for audio-visual learning
Focus on automated visual translation
Contribute to the development of various products based on proprietary research

Skills

Key technologies and capabilities for this role

PythonPyTorchTensorFlow3D Computer VisionSpeech SynthesisComputer GraphicsSignal ProcessingAudio-Visual LearningMultimodal FusionGenerative ModelsAttention ModelsDeep Neural Networks

Questions & Answers

Common questions about this position

What is the salary range for this Research Engineer position?

The salary range is $175,000 - $210,000 a year.

Is this role remote or does it require office work?

This information is not specified in the job description.

What are the key skills and qualifications required for this role?

Candidates need a Ph.D. or postdoctoral experience in 3D Computer Vision, Speech Synthesis, or related fields, 6+ years in Python with PyTorch or TensorFlow, a strong publication record in top venues like CVPR and SIGGRAPH, and expertise in audio-visual learning, multimodal fusion, and 3D audio-driven face animation.

What is the company culture like at Flawless AI?

The role involves working with and leading a close-knit, passionate group of world-class individuals in a dynamic and collaborative environment focused on tackling challenging problems in deep learning and shaping the future of filmmaking.

What should I expect in the interview process and how can I prepare?

The process includes four rounds with occasional Zoom or in-person coffee meetings, starting with a 30-45 minute recruiting screen discussing background, interests, and motivations, designed to simulate working together and explore past projects.

Flawless

AI-driven visual translation for films

About Flawless

Flawless AI specializes in visual translation technology for the TV and film industry. Their main product, TrueSync, uses artificial intelligence to translate foreign language films into the native language of viewers while maintaining accurate lip-sync and photorealistic visuals. This ensures that the original performances of actors are preserved, creating an authentic viewing experience. Flawless AI differentiates itself from competitors by focusing on seamless visual translation that allows filmmakers and content owners to reach global audiences without losing the essence of their work. The company's goal is to enhance the global distribution of films and TV shows, making them accessible to diverse audiences while respecting the original artistic intent.

London, United KingdomHeadquarters

2018Year Founded

$1.7MTotal Funding

SEEDCompany Stage

AI & Machine Learning, EntertainmentIndustries

201-500Employees

Benefits

Hybrid Work Options

Stock Options

Risks

Competition from generative AI companies like Colossyan threatens Flawless's market share.

Rapid AI development in the UK may lead to market saturation and increased competition.

Stricter regulations from the Bletchley Declaration could impact Flawless's innovation capabilities.

Differentiation

TrueSync offers AI-driven lip-syncing for multilingual film visualizations, preserving original performances.

Flawless AI targets filmmakers seeking global distribution without losing artistic integrity.

The company provides a unique solution for seamless visual translation in the film industry.

Upsides

Growing demand for AI localization tools as global streaming platforms expand content libraries.

Partnership opportunities with major streaming services investing in AI for content delivery.

Increased focus on AI ethics could position Flawless as a leader in responsible AI use.

Land your dream remote job 3x faster with AI

Try Jobo Free