Research Scientist (Generative Modeling)

About the job

Responsibilities

• Design, implement, and train large-scale diffusion models for generating 3D worlds.
• Develop and experiment with diffusion models to add novel control signals, adapt to aesthetic preferences, or distill for efficient inference.
• Collaborate with research and product teams to translate product requirements into technical roadmaps.
• Contribute to all stages of model development, including data curation, experimentation, evaluation, and deployment.
• Explore and integrate cutting-edge research in diffusion and generative AI.
• Act as a key technical resource, mentoring colleagues and driving best practices in generative modeling and ML engineering.

Requirements

• 3+ years of experience in generative modeling or applied ML roles, ideally in a startup or fast-paced research environment.
• Extensive experience with machine learning frameworks like PyTorch or TensorFlow, particularly with diffusion and other generative models.
• Deep expertise in at least one area of generative modeling (pre-training, post-training, diffusion distillation, fine-tuning with new conditioning signals).
• Strong history of publications or open-source contributions involving large-scale diffusion models.
• Strong coding proficiency in Python and experience with GPU-accelerated computing.
• Ability to effectively communicate complex technical ideas to researchers and cross-functional teams.
• Comfortable operating in a dynamic startup environment with ambiguity and high ownership.