Overview
Develop and implement novel machine learning systems that generate realistic human-like animations at production scale. This is a research-adjacent role requiring both academic understanding of state-of-the-art techniques and practical engineering skills with Unreal Engine to deploy models in production pipelines.
Key Responsibilities
- Design, train, and deploy ML models for realistic human-like animation generation
- Research and implement cutting-edge techniques from recent papers (motion diffusion, neural character animation, etc.)
- Optimize models for speed and quality to handle production-scale requirements
- Build data preprocessing pipelines and manage training datasets
- Collaborate with animators to understand quality requirements and refine model outputs
- Integrate ML systems with existing pipeline tools and Unreal Engine workflows
- Monitor and improve model performance, addressing edge cases and quality issues
- Document systems and create guidelines for artists working with generated content
Required Qualifications
- 3+ years of experience in machine learning engineering, with focus on computer vision, animation, or graphics
- Strong background in deep learning frameworks (PyTorch, TensorFlow)
- Experience with motion capture data, skeletal animation, or character movement
- Knowledge of recent ML animation techniques (motion matching, diffusion models, neural networks for animation)
- Proficiency in Python and C++ for production-level code
- Experience deploying ML models in production environments
- Understanding of real-time constraints and optimization for interactive applications
- Fluent English for collaboration with international research community and internal teams
Essential Soft Skills
- Team player: Works closely with technical artists and animators to align ML outputs with creative needs
- Proactive mindset: Stays current with latest research, experiments with new techniques independently
- Motivation to grow: Genuinely excited about pushing boundaries of what's possible in animation technology
- Pragmatic approach: Balances academic rigor with practical production requirements
- Clear communicator: Can explain complex ML concepts to non-technical team members
- Iterative mindset: Comfortable with rapid experimentation and learning from failures
- Office presence: On-site availability for collaborative problem-solving and cross-team integration