Senior Speech Synthesis & Multimodal LLM Researcher

L&Q OASIS LIMITED; Greater London; Presencial; GBP 90.000 - 150.000; Jornada completa

Descripción de la vacante

Lightspeed Studios' Lightspeed Tech Center is seeking a PhD-level researcher to push the boundaries of speech synthesis, voice generation, and multimodal LLMs for real-time applications. You will collaborate with research and engineering teams from prototyping to production, delivering scalable audio solutions across games and related media.

The role focuses on advancing diffusion/ autoregressive style models, streaming dialogue, and speech-text integration, with opportunities to publish in top

Formación

• Ph.D. in Computer Science, Electrical Engineering, Signal Processing, or a closely related field.
• Strong foundation in speech/audio processing and modern generative models.
• Hands-on experience extending LLMs to speech/audio modalities and real-time interaction modeling.

Responsabilidades

• Research and develop advanced speech synthesis and generation algorithms (e.g., TTS, voice conversion, sound/music generation) based on LLMs, multimodal/omnimodal LLMs.
• Develop and optimize speech and audio synthesis systems for online applications, improving effectiveness, efficiency, and scalability.
• Explore and advance full-duplex/streaming multimodal LLM capabilities in speech understanding, generation, and real-time spoken interaction.

Conocimientos

Speech processing

Generative models

Python

PyTorch

Distributed training

Publications

Educación

Ph.D. in CS/EE/Signal Processing

Herramientas

PyTorch

Python

Descripción del empleo

Lightspeed Studios' Lightspeed Tech Center is seeking a PhD-level researcher to push the boundaries of speech synthesis, voice generation, and multimodal LLMs for real-time applications. You will collaborate with research and engineering teams from prototyping to production, delivering scalable audio solutions across games and related media.

The role focuses on advancing diffusion/ autoregressive style models, streaming dialogue, and speech-text integration, with opportunities to publish in top