Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Описание вакансии
Текст:
TL;DR
Staff Research Scientist (AI) (Generative AI/video diffusion): Building avatar-centric, interactive video diffusion models that understand user audio and video and generate natural real-time conversational reactions with an accent on multimodal interaction, turn-taking, and perceptual modeling. Focus on setting research direction, adapting diffusion models to conversational conditioning, developing evaluation frameworks, and leading research from experimentation to production.
Location: Europe; hybrid work is available from offices in London, Amsterdam, Zurich, or Munich, or remotely within Europe.
Company
Synthesia develops an AI video platform for business and enterprise skill development, with products built by in-house AI researchers and engineers.
What you will do
- Set the research direction and roadmap for dyadic interaction modeling while balancing long-term research with near-term product impact.
- Advance multimodal perception and generation for interactive agents that understand user audio and video and produce contextually appropriate reactions.
- Post-train multimodal models and adapt diffusion models to conversational state, turn-taking, and listener cues.
- Build evaluation frameworks and test suites for continuous tracking of interaction quality.
- Define data needs and shape high-quality datasets with the data team.
- Lead and mentor researchers and drive technical decisions across research, data, and engineering.
Requirements
- Deep machine learning expertise and extensive hands-on experience with diffusion models, ideally for video or avatar generation.
- Strong publication record at top-tier machine learning or computer vision venues, or equivalent demonstrated impact.
- Experience leading a small research team, mentoring junior researchers, and taking research from idea to production.
- Proficiency in PyTorch and modern tooling for large-scale machine learning training.
- Clear communication of hypotheses, experiments, and results, with the ability to influence direction across teams.
- Ability to work remotely from Europe or from a listed European office location.
Nice to have
- Experience with real-time or streaming generation, including autoregressive video diffusion.
- Distillation or other techniques for low-latency inference.
- Audio-driven facial, gesture, or full-body motion modeling.
- Conversational modeling involving turn-taking, backchanneling, or listener-response generation.
Culture & Benefits
- Fast-moving environment focused on building and shipping generative AI products.
- Work with a team of more than 40 researchers and engineers on interactive avatars.
- 25 days of annual leave plus public holidays.
- Regular planning sessions and social events at company hubs.
- Competitive compensation and additional benefits depending on location.
- Focus on AI safety, ethics, security, and people-first product development.
Будьте осторожны: если работодатель просит войти в их систему, используя iCloud/Google, прислать код/пароль, запустить код/ПО, не делайте этого - это мошенники. Обязательно жмите "Пожаловаться" или пишите в поддержку. Подробнее в гайде →