Synthesia is seeking a Staff Research Engineer to join the Voice team and help drive a broader multimodal vision. You will own design and implementation of critical components, working with senior engineers across voice and video domains.
You will shape roadmaps, develop low-latency, conversational voice-video systems, and ship models to production. The role demands deep expertise in generative modelling, transformer architectures, and end-to-end training, with strong software engineering skills
#J-18808-Ljbffr
