Member of Technical Staff - Image / Video Generation

Black Forest Labs · Freiburg (Germany) · Posted Sep 17, 2024


Transparency

Dead

Online for 113 weeks and never reposted. Jobs this old or reposted this often rarely lead to a hire. It may be filled already.

First seen
Oct 6, 2026
Offered for
794 days

Overview

Category
AI & machine learning
Employment type
Permanent
Workplace type
On-site
Country
Germany
Seniority
Staff
Schedule
Full time
Salary
Not listed

Key skills

Large‑scale diffusion model training
Train diffusion transformer models on image and video data at research scale and handle failure modes.
Diffusion model fine‑tuning
Adapt diffusion models for specialized tasks such as upscaling, inpainting or outpainting.
Generative model evaluation
Assess image and video generation quality using appropriate metrics and correlate them with perceptual quality.
PyTorch research coding
Write reproducible research code in PyTorch that can be built upon by other team members.
Distributed training techniques
Implement and troubleshoot FSDP, low‑precision training and model parallelism for multi‑GPU workloads.
Multi‑agent workflow management
Orchestrate coding agents and other automated tasks to accelerate experiments while ensuring quality.

Key phrases

  • large-scale diffusion models
  • image and video generation
  • speed-quality tradeoffs
  • image and video upscalers
  • inpainting/outpainting
  • multi-agent workflows
  • distributed training techniques
  • FSDP
  • low precision training
  • model parallelism
  • forward and backward Triton kernels
  • Nsight

From the posting

About Black Forest Labs

We’re the team building the foundational layer for visual intelligence: multimodal models trained jointly on images, video, audio, and action to see, generate, and understand the world.

Our founding team pioneered latent diffusion and Stable Diffusion, the breakthroughs that made generative AI accessible to millions. With FLUX, we're pushing into generative media at scale, machines that act in the physical world, and emerging applications in computer use.

Our FLUX models top public benchmarks and run in production in some of the world's biggest platforms. We're a small, fast growing research lab competing with the largest companies in the world. From our labs in Freiburg to San Francisco, we're building what comes next.

Why This Role

You'll train large-scale diffusion models for image and video generation, exploring new approaches while maintaining the rigor that helps us distinguish meaningful progress from incremental tweaks. This isn't about following established recipes—it's about running the experiments that clarify which architectural choices matter and which are less impactful.

What You’ll Work On

  • Trains large-scale diffusion transformer models for image and video data, working at the scale where intuitions break and empirical evidence matters

  • Rigorously ablates design choices—running experiments that isolate variables, control for confounds, and produce insights you can actually trust—then communicating those results to shape our research direction

  • Reasons about the speed-quality tradeoffs of neural network architectures in production settings where both constraints matter simultaneously

  • Fine-tunes diffusion models for specialized applications like image and video upscalers, inpainting/outpainting models, and other tasks where general-purpose models aren't enough

What We’re Looking For

You've trained large-scale diffusion models and developed strong intuitions about what matters. You know that at research scale, every design choice has tradeoffs, and the only way to know which ones are worth making is through careful ablation. You're comfortable debugging distributed training issues and presenting research findings to the team.

You likely have:

  • 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 PyTorch fluency; you write research code that others can build on. You work fluently with coding agents to move faster, and have the depth to verify their output and own the result.

  • Experience running multi-agent workflows: you know which tasks to hand off and which to keep yourself, and you use the speed-up to raise the quality bar, not lower it.

  • 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

We'd be especially excited if you:

  • Have experience writing forward and backward Triton kernels and ensuring their correctness while considering floating point errors

  • Bring proficiency with profiling, debugging, and optimizing single and multi-GPU operations using tools like Nsight or stack trace viewers

  • Know the performance characteristics of different architectural choices at scale

  • Have published research that contributed to how people think about generative models

How We Work Together

We’re a distributed team with real offices that people actually use. This role is based in Freiburg, and you’ll join us in the office at least 2 days a week, or one full week every other week.

Everything we do is grounded in four values:

  • Obsessed. We are a frontier research lab. The science has to be right, the understanding deep, the product beautiful.

  • Low Ego. The work speaks. The best idea wins, no matter who said it. Credit is shared. Nobody is above any task.

  • Bold. We take the ambitious bet. We ship, we do not wait for conditions to be perfect.

  • Kind. People over politics. We treat each other with genuine warmth. Agency without empathy creates chaos.

If this sounds like work you’d enjoy, we’d love to hear from you.

Base Annual Salary:

EU €130,000-€340,000 + Equity

Note: We may use AI-assisted tools to help organize applications. All hiring decisions are always made by our team.

More jobs at Black Forest Labs

Research Lead, Evaluations

Black Forest Labs · 2 days ago | Freiburg (Germany) | On-site · Lead · Full time

Create CV

Machine Learning Engineer - AI Safety

Black Forest Labs · 4 days ago | San Francisco (United States) | On-site · Staff · Full time

Create CV

Member of Technical Staff - Infrastructure Security

Black Forest Labs · 4 days ago | Remote, San Francisco (United States), Freiburg (Germany) | $220K–$280K / year | Remote · Staff · Full time

Create CV

Member of Technical Staff - Workforce Security

Black Forest Labs · 4 days ago | Remote, San Francisco (United States), Freiburg (Germany) | $180K–$225K / year | Remote · Staff · Full time

Create CV

Privacy & Product Counsel

Black Forest Labs · 2 weeks ago | Freiburg (Germany), Berlin (Germany), San Francisco (United States) +3 | Remote · Senior · Full time

Create CV
See all 17 jobs at Black Forest Labs