Staff Research Engineer - Multimodal Generative Modelling

About the role

Synthesia is seeking a Staff Research Engineer to join their R&D department and drive the development of human-interactive models that combine text, audio, and video. You will define research roadmaps, design and implement critical system components, and collaborate with cross-functional teams to ship real-time, conversational AI experiences. The role focuses on creating models that perceive and respond to user actions and emotions with natural, low-latency interaction.

Responsibilities

• Shape the roadmap to create new model capabilities and unlock new functionality for customers.
• Propose novel multi-modal system architectures, particularly for text and voice.
• Develop and evaluate streaming and conversational systems for low-latency, interactive voice-video synthesis.
• Design solutions that reinforce emotional expressiveness and natural interaction.
• Implement and bring designs to life, from pretraining through post-training.
• Integrate and test novel architectures like neural codecs, diffusion, and flow-matching to enhance realism.
• Define new evaluation metrics for conversational systems, including latency-aware and interaction-based measurements.
• Lead post-training initiatives such as DPO, fine-tuning, and distillation to bring models to production quality.

Required skills

• Generative modelling
• Large language models
• Transformer-based architectures
• PyTorch
• Distributed training
• Model optimization
• Time-series modeling
• Tokenization
• Deep learning
• Software engineering

Nice to have

• Real-time architectures
• Streaming architectures
• Diffusion models
• Neural codecs
• Flow-matching models
• Autoregressive decoders
• Voice
• Text
• Video

About the Company

Synthesia is the world’s leading AI video platform for business, used by over 90% of the Fortune 100. Founded in 2017, the company is headquartered in London and develops products to enhance visual communication and enterprise skill development.