обновлено 9 часов назад
Research Scientist (Generative AI)
Вакансия из Hirify Global, списка международных tech-компанийДля мэтча и отклика нужен Plus
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Описание вакансии
Текст:
TL;DR
Research Scientist (Generative AI): Building avatar-centric, interactive video diffusion models for real-time AI agents with an accent on multimodal perception, conversational interaction, and human-like reactions. Focus on adapting diffusion models to conversational conditioning, post-training multimodal systems, and designing evaluation frameworks for production-scale interaction quality.
Location: Europe; remote
Company
Synthesia develops an AI video platform for business, with products focused on visual communication, enterprise skill development, and generative video.
What you will do
- Contribute to research direction for dyadic interaction modeling and own research problems end to end.
- Develop perceptual systems for interactive agents that understand user audio and video and generate contextually appropriate reactions.
- Post-train multimodal models for natural dyadic interactions, including turn-taking, backchannels, gaze, and facial and body reactions.
- Adapt diffusion models to conditioning signals such as conversational state, turn-taking, and listener cues.
- Build evaluation frameworks and test suites for interaction quality.
- Define data needs with the data team, run rigorous experiments, and communicate findings that guide technical decisions.
Requirements
- Strong machine learning background and hands-on experience with diffusion models, ideally for video or avatar generation.
- Publications at top-tier venues in areas such as world models, dyadic interaction, or video diffusion, or equivalent demonstrated impact.
- Experience taking research ideas through to working implementations and production.
- Proficiency in PyTorch and modern tooling for large-scale training.
- Clear communication of hypotheses, experiments, and results.
Nice to have
- Experience with real-time or streaming generation, including autoregressive video diffusion.
- Distillation or other low-latency inference techniques.
- Audio-driven facial, gesture, or full-body motion modeling.
- Conversational modeling, including turn-taking, backchanneling, or listener-response generation.
- Experience mentoring students or junior researchers.
Culture & Benefits
- Work on production-scale video foundation models in a fast-growing generative AI company.
- Develop human-centric video generation with real-world impact.
- Solve challenges in scaling, stability, and controllability.
- Work in a highly technical, high-ownership environment where research ships into products.
- Collaborate with AI researchers and engineers on in-house technology, with a focus on AI safety, ethics, and security.
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 →