Research Engineer

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, with offices and teams across Europe and the US. As AI continues to shape the way we live and work, Synthesia develops products to enhance visual communication and enterprise skill development, helping people work better and stay at the center of successful organizations. Following our Series E funding, Synthesia aims to build human-interactive models that perceive and respond to users, combining text, audio and video in real-time. As a Staff Research Engineer, you will join the Voice team within the 40+ person R&D department, but your scope extends beyond voice. You will define and drive broader vision across teams, own the design and implementation of critical components, and collaborate with senior members across video and research. You will work on voice-to-voice models that produce text and voice simultaneously, enabling natural conversations with back-channeling. Responsibilities include shaping roadmaps, proposing multi-modal architectures, developing streaming conversational systems, designing emotionally expressive interactions, implementing designs from pretraining to post-training, testing architectures, defining evaluation metrics, tracking research in audio-visual diffusion and multimodal LLMs, curating data, leading post-training initiatives, and shipping models to production. You will thrive if you can bring novel ideas, have strong PyTorch experience, time-series knowledge, and a track record of end-to-end model training. Bonus points for real-time architectures, diffusion and neural codec familiarity, and publications.