← All roles

Staff Research Engineer - Multimodal Generative Modelling

Synthesia· Research and Development
Apply on company site
RemoteFull-timePosted 3mo ago

About the role

Staff Research Engineer focusing on multimodal, real-time generative modelling (text, audio, video) to advance interactive voice-video synthesis. Lead roadmap, design, implementation, and production deployment of next-generation multimodal systems within Synthesia’s Voice and broader R&D teams.

Responsibilities

  • Shape our roadmap to create new model capabilities and unlock new functionality for our customer base, on both short and long time horizons.
  • Propose novel multi-modal system architectures (especially 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 (neural codecs, diffusion, flow-matching) to enhance realism and responsiveness.
  • Define new evaluation metrics for conversational systems, including latency-aware and interaction-based measurements.
  • Track the latest research in audio-visual diffusion, autoregressive models, neural codecs, and multimodal LLMs.
  • Curate new datasets to complement existing data.
  • Lead post-training initiatives like DPO, fine-tuning, and distillation to bring models to shipping quality.
  • Ship models to production with optimised runtime to serve customers, and address their feedback thereafter.

Qualifications

  • The ability to bring novel ideas and designs that advance the field of interactive multimodal systems.
  • Strong understanding of generative modelling, ideally applied to sequential or multimodal data.
  • Hands-on experience with large language models or similar transformer-based architectures.
  • High proficiency in PyTorch, including distributed training and model optimization.
  • A solid grasp of time-series modeling and tokenization, preferably in the context of audio, speech, or video.
  • A demonstrated ability to prototype quickly, test hypotheses, and iterate efficiently.
  • Proven experience training deep learning models end-to-end, from data preparation through evaluation.
  • Strong general software engineering skills, enabling contributions to a large, shared research infrastructure.

Skills

Required:Novel ideas and architectural designGenerative modelling (sequential / multimodal)Large language models / transformer architecturesPyTorch (distributed training, optimization)Time-series modeling and tokenization (audio/speech/video)Prototyping, hypothesis testing, and iterationEnd-to-end DL model training
Last updated Jul 22, 2026. Interested? Apply on the company site.

About Synthesia

#1 AI Video Platform for Business

Synthesia is a #1 AI Video Platform for Business. Our AI Video Generator enables anyone to create professional videos without mics, cameras, actors, or studios. Using AI, we’re radically changing the process of video content creation, making it scalable and affordable while maintaining high quality.

AI Video GeneratorAI Video PlatformCorporate VideoCustom AvatarsLanguagesLocalizationTraining VideosVideo Production
Company profileWebsite

More open roles at Synthesia