Member of Technical Staff - Image / Video Researcher Freiburg (Germany), San Francisco (USA)

Global Trade Plaza; Mississippi; On-site; USD 80,000 - 150,000; Full time

Job summary

Join a pioneering startup at the forefront of generative image and video technology. As a member of the technical staff, you will engage in training and developing large scale Diffusion models, contributing to innovative projects that push the boundaries of image and video generation. This role offers the opportunity to work with cutting-edge technology and collaborate with a talented team that has made significant advancements in the field. If you are passionate about AI and eager to make a meaningful impact in a dynamic environment, this position is perfect for you.

Qualifications

• Experience in training and finetuning large scale Diffusion models for image and video.
• Strong proficiency in PyTorch and understanding of neural network architectures.

Responsibilities

• Train large scale Diffusion models for image and video data.
• Communicate design choices and results with the broader team.

Skills

Training large scale Diffusion models

Finetuning Diffusion models

PyTorch

Neural network architectures

Training techniques (FSDP, low precision training)

Profiling and debugging GPU operations

Tools

Nsight

Triton

Job description

Member of Technical Staff - Image / Video Researcher

Remote | Germany | USA

Black Forest Labs is a cutting-edge startup pioneering generative image and video models. Our team, which invented Stable Diffusion, Stable Video Diffusion, and FLUX.1, is currently seeking a strong researcher to work on model training and development.

Role:

• Training large scale Diffusion (transformer) models for image and video
• Rigorously ablating design choices and communicating results & decisions with the broader team
• Reasoning about the speed and quality trade-offs of neural network architectures

Ideal Experiences:

• Training large scale Diffusion models for image and video data
• Finetuning Diffusion models for image and video applications, such as image and video upscalers, in and out painting models, etc.
• Deep understanding of how to effectively evaluate image and video generative models
• Strong proficiency in PyTorch, transformer models, and other NN architectures.
• Deep understanding of training techniques such as FSDP, low precision training, and model parallelism

Nice to have:

• Experience with writing forward and backward Triton kernels and ensuring their correctness while considering floating point errors
• Profiling, debugging, and optimizing single and multi-GPU operations using tools such as Nsight or stack trace viewers