Embodied AI Research Scientist — Real-Time 3D Synthesis

Thespian Labs; Somerville, Northern (MA, KY); Hybrid; USD 120,000 - 180,000; Full time

Benefits offered by this job

Visa sponsorship

Equal opportunity employer

Job summary

Thespian Labs is seeking an AI Research Scientist to design and implement state-of-the-art generative models that power embodied behavior. You will work with diffusion-based and transformer architectures to synthesize 3D content, motion, and audio for real-time control of humanoids and digital characters.

You will own research problems end to end, collaborating with data and engineering teams to turn large-scale datasets into observable behavior.

Qualifications

• Proven experience developing and training deep learning models, particularly transformers and/or diffusion models.
• Strong programming skills in Python and proficiency with modern ML frameworks like PyTorch.
• Solid understanding of 3D computer vision and geometry, including how shape, motion, and space are represented and generated.
• A strong portfolio of publications at top-tier conferences such as CVPR, ICCV, or NeurIPS.
• Ability to take a model from research to a system that runs, with care for quality, performance, and scale.

Responsibilities

• Develop and train advanced generative models, particularly diffusion-based architectures, for high-fidelity 3D content in real time.
• Explore and implement cutting-edge techniques across generative modeling, including visual, motion, and audio components.
• Design the system to combine multiple model types into a single forward pass rather than a pipeline.
• Collaborate with data engineering to define data requirements and use large-scale datasets for training.
• Optimize models for quality, performance, and scalability to run in live scenarios and on robots.
• Stay current with the latest research in generative AI and 3D computer vision and bring findings into work quickly.
• Take research from idea to deployment, owning problems end to end with real humanoids and live digital characters.

Skills

Deep learning

Transformers

Diffusion models

Python

3D computer vision

Research publications

End-to-end deployment

Tools

PyTorch

Job description

Thespian Labs is seeking an AI Research Scientist to design and implement state-of-the-art generative models that power embodied behavior. You will work with diffusion-based and transformer architectures to synthesize 3D content, motion, and audio for real-time control of humanoids and digital characters.

You will own research problems end to end, collaborating with data and engineering teams to turn large-scale datasets into observable behavior.