Synthesia

6 months ago

Senior Research Engineer - Voice

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI

Last checked: 11 hours agoStatus: Live

Job Summary

Senior Research Engineer in the Audio Post-Training team applying generative modelling and transformer-based architectures to speech and voice synthesis. Work on production-ready voice models, end-to-end DL pipelines, and advanced post-training optimization, with a focus on real-time, high-quality TTS outputs and deploying across a large research infrastructure.

Location: London

Workplace: Hybrid

Employment Type: Full time

Job Function: Education & Training

Seniority: Sr. Manager level

Key Responsibilities

•Adapt models for new conditioning inputs (emotion, speed, prosody, speaker control, etc.).
•Fine-tune and optimize speech models using techniques such as Direct Preference Optimization (DPO) and LoRA.
•Implement post-training optimization techniques (quantization, pruning, distillation) to improve efficiency and latency for real-time speech generation.
•Integrate and test novel architectures (neural codecs, diffusion, flow-matching models) to enhance realism and responsiveness.
•Design and implement new evaluation metrics for TTS systems, including MOS prediction models.

Pay and Benefits

Perks:EquityAnnual BonusRemote WorkAnnual Leave

Key Requirements

•Strong understanding of generative modelling applied to sequential or multimodal data.
•Hands-on experience with large language models (LLMs) or transformer-based architectures.
•High proficiency in PyTorch, including distributed training and model optimization.
•Solid grasp of time-series modelling and tokenization in audio or speech contexts.
•Proven ability to prototype quickly, test hypotheses, and iterate efficiently.

Experience:Generative AISpeechLLMsAudioTransformers

Skills:Problem-solvingCommunicationPrototypingTeamwork

Languages:English

Tech Stack:PythonPyTorchLLMsTransformersDistributed trainingDiffusionNeural codecsSpeechTTSMOSQuantizationPruning

Company Brief

Synthesia

Provides an AI video generation platform that creates realistic synthetic presenters and video content from text, enabling enterprises to produce scalable training, marketing, and communications videos without cameras or actors.

Industry: AI & Machine Learning

Company Size: Large (251 to 1,000 employees)

Growth: Scaleup

Valuation: Unicorn (USD 1B+)

Funding: Series C

Headquarters: London, United Kingdom

Founded: 2017

Website LinkedIn

Loading job details...

Preparing the role view and application actions.

Synthesia

6 months ago

Senior Research Engineer - Voice

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI

Last checked: 11 hours agoStatus: Live

Job Summary

Location: London

Workplace: Hybrid

Employment Type: Full time

Job Function: Education & Training

Seniority: Sr. Manager level

Key Responsibilities

•Adapt models for new conditioning inputs (emotion, speed, prosody, speaker control, etc.).
•Fine-tune and optimize speech models using techniques such as Direct Preference Optimization (DPO) and LoRA.
•Implement post-training optimization techniques (quantization, pruning, distillation) to improve efficiency and latency for real-time speech generation.
•Integrate and test novel architectures (neural codecs, diffusion, flow-matching models) to enhance realism and responsiveness.
•Design and implement new evaluation metrics for TTS systems, including MOS prediction models.

Pay and Benefits

Perks:EquityAnnual BonusRemote WorkAnnual Leave

Key Requirements

•Strong understanding of generative modelling applied to sequential or multimodal data.
•Hands-on experience with large language models (LLMs) or transformer-based architectures.
•High proficiency in PyTorch, including distributed training and model optimization.
•Solid grasp of time-series modelling and tokenization in audio or speech contexts.
•Proven ability to prototype quickly, test hypotheses, and iterate efficiently.

Experience:Generative AISpeechLLMsAudioTransformers

Skills:Problem-solvingCommunicationPrototypingTeamwork

Languages:English

Tech Stack:PythonPyTorchLLMsTransformersDistributed trainingDiffusionNeural codecsSpeechTTSMOSQuantizationPruning

Company Brief

Synthesia

Industry: AI & Machine Learning

Company Size: Large (251 to 1,000 employees)

Growth: Scaleup

Valuation: Unicorn (USD 1B+)

Funding: Series C

Headquarters: London, United Kingdom

Founded: 2017

Website LinkedIn