[All remote jobs](https://jobicy.com/jobs.md)Open role[![Synthesia logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2026/06/c69aad11-221.webp)](https://jobicy.com/company/synthesia.md)Remote opportunity at[Synthesia](https://jobicy.com/company/synthesia.md)

# Senior Research Engineer – Voice

Review the role, location requirements, compensation details, and application process before deciding whether this opportunity fits your next career move.

[Apply for this job](#job-application)[View company](https://jobicy.com/company/synthesia.md)Share19 Aug 2026Published32Listing views3Application actions18 Sep 2026Apply before  Opportunity details

## About this role.

AI SummarySynthesia is hiring a Senior Research Engineer to develop production-quality generative speech and voice-synthesis systems. The role focuses on streaming speech-to-speech models, expressive voice conditioning, post-training optimization, and low-latency inference. The engineer will work within a 40+ person R&D organization and contribute directly to voice models used in a commercial AI video platform. Success requires strong practical machine learning expertise, PyTorch proficiency, and the ability to rapidly prototype, evaluate, and productionize advanced audio-modeling approaches. Experience with speech generation, neural codecs, diffusion, LLMs, and distributed training is especially relevant.

## Role DNA

A quick view of the complexity, pace, ownership and collaboration implied by the job description.

### Job Complexity

5/5EasyHard

### Pace & Pressure

4/5RelaxedFast-paced

### Autonomy Level

4/5GuidedFull ownership

### Communication Load

4/5IndependentCollaborative

AI insightThis is a highly specialized senior research engineering position spanning state-of-the-art generative modeling, real-time speech systems, distributed training, and production optimization. Candidates must bridge research experimentation with reliable, latency-sensitive implementation in a shared engineering environment.

## Salary analysis

Estimated compensation compared with the broader US market for similar roles.

Estimated job medianHighly competitive$230,000US market range$190k–$270k0$297k

AI insightNo salary range is disclosed in the posting, so these figures are estimated for the US market in USD. A senior research engineer specializing in generative AI, speech synthesis, distributed PyTorch training, and real-time inference commonly earns an estimated base-salary range of $190,000 to $270,000, with a midpoint estimate of $230,000; equity, bonus, and location can materially affect total compensation.

## Core skills

Skills and capabilities most closely associated with this opportunity.

[Generative AI](https://jobicy.com/jobs?search_keywords=Generative%20AI.md)[Speech Synthesis](https://jobicy.com/jobs?search_keywords=Speech%20Synthesis.md)[Voice Generation](https://jobicy.com/jobs?search_keywords=Voice%20Generation.md)[PyTorch](https://jobicy.com/jobs?search_keywords=PyTorch.md)[Large Language Models](https://jobicy.com/jobs?search_keywords=Large%20Language%20Models.md)[Distributed Training](https://jobicy.com/jobs?search_keywords=Distributed%20Training.md)[Deep Learning](https://jobicy.com/jobs?search_keywords=Deep%20Learning.md)[Model Optimization](https://jobicy.com/jobs?search_keywords=Model%20Optimization.md)[Real-Time Systems](https://jobicy.com/jobs?search_keywords=Real-Time%20Systems.md)[Audio Modeling](https://jobicy.com/jobs?search_keywords=Audio%20Modeling.md)

Cover letter sampleDear Synthesia Hiring Team,

I am excited to apply for the Senior Research Engineer - Voice role. My background in generative modeling, transformer-based systems, and end-to-end deep-learning development aligns closely with your work on expressive, real-time synthetic speech.

I would bring a practical research-engineering approach to prototyping, evaluating, and optimizing voice models, including distributed PyTorch training, post-training techniques, and latency-sensitive inference. I am particularly motivated by the opportunity to help deliver robust speech-to-speech and conversational voice capabilities at production scale.

I would welcome the opportunity to discuss how my experience can contribute to Synthesia's Audio Post-Training Team.

Copy   Sample interview questionsDescribe how you would evaluate a streaming speech-to-speech system beyond offline audio-quality metrics.I would combine perceptual quality measures such as MOS or learned MOS predictors with streaming-specific measures: time to first audio, end-to-end turn latency, chunk-boundary artifacts, interruption handling, real-time factor, and stability under network or compute variation. I would also run human evaluation on conversational scenarios, because natural turn-taking and responsiveness often reveal failures not captured by offline metrics.

How would you choose among quantization, pruning, and distillation for reducing voice-model inference latency?

I would first profile the serving stack to identify whether latency is dominated by model compute, memory bandwidth, codec stages, or orchestration. Quantization is often the first option for reducing memory and accelerating supported kernels; distillation is appropriate when a smaller student can retain quality; pruning can help when the deployment runtime exploits sparsity effectively. I would validate each approach against quality, speaker similarity, prosody control, real-time factor, and production hardware constraints.

What are the main challenges in adding emotion, speed, and speaker controls to a generative speech model?

The controls must be well represented in training data, disentangled enough to avoid unwanted changes in linguistic content or identity, and consistently followed at inference. I would use structured conditioning inputs, targeted data balancing, control-specific evaluation sets, and preference or ranking objectives where appropriate. I would also test compositional controls, such as an emotional speaking style at a faster rate, to identify interaction failures.

How have you approached distributed training for large deep-learning models in PyTorch?

I would use distributed data parallelism as a baseline and select sharding approaches such as FSDP when model or optimizer memory requires it. Important considerations include efficient data loading, mixed precision, gradient accumulation, checkpoint reliability, reproducibility, communication overhead, and monitoring training quality across workers. I would benchmark throughput and memory while ensuring that distributed behavior matches single-node validation results.

How would you decide whether a new diffusion, flow-matching, or neural-codec architecture is worth integrating into a production voice stack?

I would define explicit acceptance criteria covering speech naturalness, intelligibility, speaker similarity, controllability, streaming latency, cost, robustness, and maintainability. After reproducing a credible baseline, I would run controlled experiments against the current system on representative languages, voices, and conversational use cases. I would recommend integration only if the quality and operational gains justify the added serving complexity and can be sustained with reliable evaluation and monitoring.

Synthesia is the world’s leading AI video platform for business, used by over 90% of the Fortune 100. Founded in 2017, the company is headquartered in London, with offices and teams across Europe and the US.

As AI continues to shape the way we live and work, Synthesia develops products to enhance visual communication and enterprise skill development, helping people work better and stay at the center of successful organizations.

Following our recent Series E funding round, where we raised $200 million, our valuation stands at $4 billion. Our total funding exceeds $530 million from premier investors including Accel, NVentures (Nvidia’s VC arm), Kleiner Perkins, GV, and Evantic Capital, alongside the founders and operators of Stripe, Datadog, Miro, and Webflow.

### What you’ll do at Synthesia

As a Research Engineer you will join a team of 40+ Researchers and Engineers within the R&D Department working on cutting-edge challenges in the Generative AI space, with a focus on creating high-quality, expressive and real-time synthetic voices. Within the team you’ll have the opportunity to work on the applied side of our research efforts and directly impact our solutions that are used worldwide by over 60,000 businesses.

If you are an expert in ML, LLMs, speech generation, conversational models, this is your chance to make a global impact. You will join our Audio Post-Training Team, which works on generative speech and voice synthesis, ensuring our in-house voice models reach production-level quality, speed, and robustness. Typical projects include:

*

Develop and evaluate streaming and speech-to-speech systems, enabling low-latency, interactive voice synthesis.

*

Adapt models for new conditioning inputs (emotion, speed, prosody, speaker control, etc.).

*

Implement post-training optimization techniques (quantization, pruning, distillation) to improve efficiency and latency in real-time speech generation.

*

Integrate and test novel architectures, such as neural codecs, diffusion, or flow-matching models, to enhance realism and responsiveness.

*

Contribute to defining new evaluation metrics for conversational speech, including latency-aware and online MOS prediction systems.

*

Stay updated with the latest research in audio diffusion, autoregressive models, neural codecs, and multimodal LLMs.

*

Apply DPO (Direct Preference Optimization) and distillation to fine-tune large-scale speech models.

What we’re looking for:

*

Strong understanding of generative modeling, ideally applied to sequential or multimodal data.

*

Hands-on experience with large language models (LLMs) or similar transformer-based architectures.

*

High proficiency in PyTorch, including experience with distributed training and model optimization.

*

Solid grasp of time-series modeling and tokenization, preferably in the context of audio or speech.

*

Demonstrated ability to prototype quickly, test hypotheses, and iterate efficiently.

*

Proven experience in training deep learning models end-to-end, from data preparation to evaluation.

*

Strong general software engineering skills, enabling contributions to a large, shared research infrastructure.

Nice to have experience:

*

Experience with real-time or streaming architectures is a big plus.

*

Familiarity with state-of-the-art architectures in audio and speech generation (e.g., diffusion models, neural codecs, flow-matching models, autoregressive decoders).

*

Experience with speech-to-speech or text-to-speech (TTS) systems.

*

Evidence of original research contributions, such as publications or open-source work in top-tier venues (e.g., ICASSP, Interspeech, NeurIPS, ICML).

Show more

[Apply now >](https://jobicy.com/jobs/151156-senior-research-engineer-voice.md)

>  Annual salary information is not provided for this position. Explore salary ranges for similar roles in our [Salary Directory ›](https://jobicy.com/salaries.md)

*

![Upload CV](data:image/svg+xml;base64,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)

### Upload your resume now

To unlock remote work opportunities and be discovered by global employers.

This job listing has been manually reviewed by the Jobicy Trust & Safety Team for compliance with our posting guidelines, including verification of the company's legitimacy, accuracy of job details, clarity of remote work policy, and absence of misleading or fraudulent content.

Next step

## Apply now.

Follow the employer’s application method and review Jobicy’s safety guidance before sharing personal information.

Keep exploring

## Related remote jobs.

Matched by job category10 related opportunities[Software Engineering](https://jobicy.com/categories/engineering.md) [Browse all jobs](https://jobicy.com/jobs.md)
*
![Dispatch logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2022/01/5a628d4cc7426c31799aa35e0fbcf45e.jpeg)
Dispatch  Aug 19

### [Senior Fullstack Engineer](https://jobicy.com/jobs/151178-senior-fullstack-engineer-2.md)

About Us The financial advisory industry is a $80T market in the US, but has seen little technological innovation compared to the self-service market (Robinhood, Betterment, Wealthfront, SoFi). Client data…

*
![Monks logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2025/06/d832a699-221.jpeg)
Monks  Aug 19

### [Fullstack Engineer](https://jobicy.com/jobs/151168-fullstack-engineer.md)

Please note that we will never request payment or bank account information at any stage of the recruitment process. As we continue to grow our teams, we urge you to…

*
![Masabi logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2025/06/f2355465-221.png)
Masabi  Aug 19

### [Principal Engineer – Platform & Data](https://jobicy.com/jobs/151159-principal-engineer-platform-data.md)

About Us_// At Masabi, we’re driving the fare payment revolution, powering the journeys of millions all over the world. We build fare collection platforms that allow riders to seamlessly buy…

*
![Qventus logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2022/01/0ad7e933ffa7b62281cc4b26710abfab.jpeg)
Qventus  Aug 19

### [AI Tooling Engineer](https://jobicy.com/jobs/151154-ai-tooling-engineer.md)

On this journey for over 12 years, Qventus is leading the transformation of healthcare. We enable hospitals to focus on what matters most: patient care. Our innovative solutions harness the…

*
![Masabi logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2025/06/f2355465-221.png)
Masabi  Aug 19

### [Technical Lead](https://jobicy.com/jobs/151153-technical-lead.md)

About Us_// At Masabi, we’re driving the fare payment revolution, powering the journeys of millions all over the world. We build fare collection platforms that allow riders to seamlessly buy…

*
![Vercel logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2025/06/a6aded72-221.png)
Vercel  Aug 19

### [Member of the Technical Staff, Internal Agent](https://jobicy.com/jobs/151152-member-of-the-technical-staff-internal-agent.md)

About Vercel: Vercel is the agentic infrastructure company. We free people and agents to ship what’s next. For more than a decade, Vercel has shaped how the web is built….

*
![Synthesia logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2026/06/c69aad11-221.webp)
Synthesia  Aug 19

### [Senior Applied Research Engineer – Video Team](https://jobicy.com/jobs/151151-senior-applied-research-engineer-video-team.md)

Synthesia is the world’s leading AI video platform for business, used by over 90% of the Fortune 100. Founded in 2017, the company is headquartered in London, with offices and…

*
![emnify logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2025/06/704b455b-221.png)
emnify  Aug 19

### [Senior UICC/eUICC/eSIM Engineer](https://jobicy.com/jobs/151131-senior-uicc-euicc-esim-engineer.md)

Your Role We are looking for a hands-on UICC/eUICC/eSIM specialist to take ownership of the engineering, interoperability, and certification readiness of our Consumer eSIM (SGP.22) and IoT eUICC (SGP.32) products….

*
![Pleo logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2025/06/b27fbed2-221.jpg)
Pleo  Aug 19

### [Senior Applied AI Engineer](https://jobicy.com/jobs/151129-senior-applied-ai-engineer.md)

About Pleo Messy spend management is tricky business. And tedious processes are a lose-lose situation for all involved, not just finance. At Pleo, we’re changing that. We build spend solutions…

*
![Socket logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2025/06/1314ce3c-221.png)
Socket  Aug 19

### [Sr. Software Engineer](https://jobicy.com/jobs/151128-sr-software-engineer.md)

About Us Socket helps devs and security teams ship faster by cutting out security busywork. Thousands of orgs use Socket to safely find, audit, and manage open source code. Our…