Machine Learning Researcher
New
B
BRAHMA AIGenerative video
Source API remote eligibility restrictions: United KingdomFull-Time
Salary not disclosed
Apply NowOpens the employer's application page
Job Details
- Required Skills
- PythonMachine LearningPyTorchDeep LearningComputer Vision
Requirements
- Strong background in machine learning and deep learning, particularly generative models for video, vision, or speech.
- Hands-on experience with video synthesis, such as face reenactment, lip sync, audio-to-video generation, or avatar animation.
- Proficiency in Python and PyTorch.
- Familiarity with libraries such as MMPose, MediaPipe, or DLIB, or with image/video generation frameworks.
- Experience training large models and working with high-resolution audio/video datasets.
- Deep understanding of transformers, diffusion models, GANs, and motion representation techniques.
- Ability to work independently and drive research from idea to implementation.
- PhD in Computer Vision, Machine Learning, or a related field, and publications in top-tier conferences, is a nice to have.
- Experience with real-time inference, model optimization, or production deployment is a nice to have.
Responsibilities
- Research and develop generative video models focused on controllable facial expression, head motion, and audio-driven lip synchronization.
- Fine-tune and extend video diffusion models such as WAN and Hunyuan to improve visual realism and audio-visual alignment.
- Design training pipelines and large-scale video/audio datasets for talking-head synthesis.
- Explore controllable expression editing, multi-view consistency, and high-fidelity lip sync from speech or text prompts.
- Work with product and creative teams to ensure models meet quality and production constraints.
- Track research in video generation, speech-driven animation, and 3D-aware neural rendering.
View Full Description & ApplyYou'll be redirected to the employer's site
