Staff Speech Scientist

Job DescriptionWant to build speech AI that actually sounds human?You'll be joining a well-funded speech AI startup with strong customer traction. They're building ultra-realistic voice technology that handles natural laughter, breathing, seamless language switching, and accurate pronunciation across languages and accents.As a Staff Research Engineer, you'll work hands-on to expand their foundation models and push the boundaries of what's possible in speech AI: exploring multilingual capabilities, long-context generation, full-duplex modeling for natural conversations with interruptions, and novel architectures that balance speed with control.What you'll doConduct research to advance their core speech models and extend product capabilitiesDevelop and experiment with new model architectures and training approachesWork on large-scale model training and data systemsCollaborate with the team to take research from concept to deployed systemsWhat you'll bring3+ years of experience in speech synthesis, audio generation, or generative modelingExperience with audio generation using LLMsSolid background in modern language model architecturesProven ability to ship research into production systemsExperience training large-scale modelsNice to havePublished research in speech or generative modelingExperience with real-time speech systems or multimodal models