Staff Research Scientist, Interactive Avatars

JobgetherGenerative AI

Based in GermanyFull-TimeStaff

Salary not disclosed

Apply NowOpens the employer's application page

Job Details

Bring deep machine-learning expertise and extensive hands-on experience with diffusion models, ideally for video generation, avatar generation, or related multimodal applications.
Demonstrate a strong research track record through publications at leading conferences, including CVPR, ICCV, ECCV, NeurIPS, ICML, ICLR, or SIGGRAPH, or equivalent research impact.
Have expertise in video diffusion, world models, dyadic interaction modeling, multimodal generation, or related fields.
Have experience leading a small team of researchers and mentoring junior research talent.
Demonstrate the ability to take research concepts from initial idea through experimentation into production systems.
Be proficient in PyTorch and modern machine-learning tooling for large-scale model training.
Have a strong understanding of multimodal learning, generative modeling, and large-scale ML experimentation.
Bring analytical and problem-solving abilities and a rigorous approach to designing experiments and evaluating results.
Communicate complex technical concepts clearly, influence research direction, and collaborate across teams.
Have experience with real-time or streaming generation, including autoregressive video diffusion.
Have expertise in model distillation or other techniques for low-latency inference.
Have experience with audio-driven facial animation, gesture generation, or full-body motion modeling.

Define the research direction and roadmap for dyadic interaction modeling, balancing long-term research opportunities with product priorities.
Advance interactive AI agents’ ability to understand user audio and video and generate contextually appropriate responses.
Develop and post-train multimodal models for natural dyadic interactions from audio and video inputs.
Adapt and extend diffusion models with conversational conditioning signals such as dialogue state, turn-taking, listener cues, and contextual reactions.
Develop models that generate conversational behaviors, including gaze, facial expressions, body reactions, and backchannel responses.
Design evaluation frameworks, benchmarks, and automated test suites to measure interaction quality.
Collaborate with data specialists to define data requirements and shape datasets for model development and training.
Lead technical decisions across research, data, and engineering, aligning research goals with product requirements.
Lead and mentor a small team of researchers.
Drive research from hypothesis and experimentation through validation, productionization, and product impact.

View Full Description & ApplyYou'll be redirected to the employer's site