1 year ago

Member of Technical Staff - Image / Video Generation

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI

Last checked: 6 hours agoStatus: Live

Job Summary

Join a distributed research team training large-scale diffusion models for image and video generation. You’ll ablate design choices, evaluate architectures, and fine-tune models for specialized tasks, using PyTorch and distributed training techniques to push state-of-the-art in generative modeling across both research and production contexts.

Location: Freiburg, San Francisco

Workplace: Hybrid

Employment Type: Full time

Job Function: Creative Production (Video/Audio/Photo)

Key Responsibilities

•Train large-scale diffusion transformer models for image and video data, working at the scale where intuitions break and empirical evidence matters
•Rigorously ablate design choices—run experiments that isolate variables, control for confounds, and translate results into actionable research direction
•Assess speed-quality tradeoffs of neural network architectures in production settings where both constraints matter
•Fine-tune diffusion models for specialized applications like image/video upscalers, inpainting/outpainting, and other domain-specific tasks
•Communicate research findings to the team and collaborate with distributed colleagues to shape research strategy

Key Requirements

•Hands-on experience training large-scale diffusion models for image and video data, with practical knowledge of common failure modes and what matters most in training
•Experience fine-tuning diffusion models for specialized applications—upscalers, inpainting, outpainting, or other tasks where understanding the domain matters as much as understanding the architecture
•Deep understanding of how to effectively evaluate image and video generative models—knowing which metrics correlate with quality and which are just convenient proxies
•Strong proficiency in PyTorch, transformer architectures, and the full ecosystem of modern deep learning
•Solid understanding of distributed training techniques—FSDP, low precision training, model parallelism—because our models don’t fit on one GPU and training decisions impact research outcomes

Experience:AIMachine learningGenerative modelsDiffusion models

Skills:Problem-solvingCollaborationCommunication

Languages:English

Tech Stack:PyTorchTransformersDiffusion modelsDistributed trainingFSDPLow precision trainingModel parallelismNVIDIA NsightTriton

Company Brief

Black Forest Labs

Develops AI-driven solutions and provides machine learning consultancy to help businesses integrate advanced models and data-driven workflows. Focuses on prototyping, model deployment, and bespoke AI services to address industry-specific problems.

Industry: Consulting

Website

Loading job details...

Preparing the role view and application actions.

Black Forest Labs

1 year ago

Member of Technical Staff - Image / Video Generation

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI

Last checked: 6 hours agoStatus: Live

Job Summary

Location: Freiburg, San Francisco

Workplace: Hybrid

Employment Type: Full time

Job Function: Creative Production (Video/Audio/Photo)

Key Responsibilities

•Train large-scale diffusion transformer models for image and video data, working at the scale where intuitions break and empirical evidence matters
•Rigorously ablate design choices—run experiments that isolate variables, control for confounds, and translate results into actionable research direction
•Assess speed-quality tradeoffs of neural network architectures in production settings where both constraints matter
•Fine-tune diffusion models for specialized applications like image/video upscalers, inpainting/outpainting, and other domain-specific tasks
•Communicate research findings to the team and collaborate with distributed colleagues to shape research strategy

Key Requirements

•Hands-on experience training large-scale diffusion models for image and video data, with practical knowledge of common failure modes and what matters most in training
•Experience fine-tuning diffusion models for specialized applications—upscalers, inpainting, outpainting, or other tasks where understanding the domain matters as much as understanding the architecture
•Deep understanding of how to effectively evaluate image and video generative models—knowing which metrics correlate with quality and which are just convenient proxies
•Strong proficiency in PyTorch, transformer architectures, and the full ecosystem of modern deep learning
•Solid understanding of distributed training techniques—FSDP, low precision training, model parallelism—because our models don’t fit on one GPU and training decisions impact research outcomes

Experience:AIMachine learningGenerative modelsDiffusion models

Skills:Problem-solvingCollaborationCommunication

Languages:English

Tech Stack:PyTorchTransformersDiffusion modelsDistributed trainingFSDPLow precision trainingModel parallelismNVIDIA NsightTriton

Company Brief

Black Forest Labs

Industry: Consulting

Website