We launched recruiters.rip, let your AI apply for you. First month free with code onemonthfree

Member of Technical Staff - Safety

14 hours agoLeadSalary: 160000 - 220000 EUR / yearFreiburg, GermanyOnsiteFull TimeAiJobs by Black Forest Labs

Frontier AI research lab building the FLUX family of multimodal visual-intelligence models and delivering them through an API, playground, and open weights.

Freiburg im Breisgau, Germany
About Black Forest Labs

Black Forest Labs develops generative AI models for image, video, audio, and action prediction, alongside production API and enterprise deployment offerings.

View jobs by Black Forest Labs

Skills

Candidate Availability

About the Role

You will research and ship methods that make FLUX models safe by design, from training data to mid- and post-training, across images, video and text. You will develop safety SFT, preference optimization, RL and concept erasure methods, build data filtering at pretraining scale, make safety robust for open-weight releases, design evaluations and red-teaming, and work with pretraining and post-training teams.

Requirements

  • Hands-on research experience in visual safety of text-to-image, text-to-video or vision-language models
  • Proven experience in large-scale safety data filtering or safety mid-/post-training
  • Deep familiarity with concept erasure methods and their failure modes
  • Track record of shipping: top-venue publications paired with production impact
  • Experience with distributed training at multi-node scale
  • Strong PyTorch fluency
  • Experience working with coding agents and multi-agent workflows

Responsibilities

  • Develop mid- and post-training safety methods for FLUX models such as safety SFT, preference optimization, RL with safety rewards and concept erasure
  • Build safety data filtering classifiers and pipelines at pretraining scale
  • Make safety robust to adversarial prompts and downstream fine-tuning for open-weight releases
  • Extend safety to prompts, captions and text encoders
  • Design evaluations and red-teaming measuring harmful generations alongside quality and prompt following
  • Work with pretraining and post-training teams and publish where it makes sense

Benefits

  • Equity
  • Coverage of reasonable travel costs to the office