Back to jobs
LS
Human

Senior Researcher, Speech Synthesis and Multimodal LLM

Lightspeed Studios

Singapore-CapitaSky aijobs Today
Apply Now

Get roles like this in your inbox

New agentic AI jobs, curated every Thursday. No spam.

Skills & Keywords

Audio ProcessingAutoregressive modelsCODECDeep learningDiffusion ModelsDistributed TrainingFlow matchingLanguage ModelsLarge Language ModelsMultimodal LearningPyTorchPython

Job Description

Collaborate with research and engineering teams; Conduct speech audio processing research; Develop LLM based voice conversion; Develop multimodal speech generation systems; Explore streaming multimodal LLM capabilities; Optimize online speech and audio synthesis; Research speech synthesis algorithms;

View full posting

Similar Roles

Explore more