Dev Global Jobs
Business

Member of Technical Staff - Safety

Black Forest LabsFreiburg (Germany)Full-timeSalary not listed · Typical pay in GermanyPosted Nov 20, 2026

Black Forest Labs has an opening for a Member of Technical Staff - Safety in Freiburg (Germany). It is listed as a full-time, staff/principal-level position.

Written by Dev Global Jobs

DGJ summary of this job

Our own short read of this listing, built only from the facts it gives. The employer’s original text follows further down.

Black Forest Labs has an opening for a Member of Technical Staff - Safety in Freiburg (Germany). It is listed as a full-time, staff/principal-level position.

Skills and tools named in the text include PyTorch and LLM.

No salary is given in this listing, so check the official pay figures in the DGJ Insight section below where they exist.

The advert does not mention visa sponsorship. If you would move to Germany for this job, check the official work permit route first (DGJ Insight lists it where we have it).

Dev Global Jobs found this job on Arbeitnow on Nov 20, 2026.

Employer
Black Forest Labs
Location
Freiburg (Germany)
Job type
Full-time
Level (from the title)
staff/principal-level
Pay
Not stated by the employer
Found
Nov 20, 2026 on Arbeitnow
Employer text
852 words, about 4 min to read
Skills named in the advert
PyTorchLLM
Before you apply
  • Apply only on the official page (arbeitnow.com). Dev Global Jobs is not the employer and never asks for a fee.
  • Mirror the skills the advert names (PyTorch and LLM) in your CV where you really have them; applicant tracking systems look for these words.
  • Read the employer’s full text below (about 4 min) before you apply.
  • Build or check your CV with the free DGJ CV Builder.
Only on Dev Global Jobs

DGJ Insight

Our own data about this role and place, from official statistics and our live job index.

Updated Nov 21, 2026
Pay benchmark
Average wage, Germany
EUR 54,840 average / year

Source: OECD Average annual wages, 2025

Work permit route
  • EU Blue Card: Recognised degree and a job offer above the salary threshold
  • Skilled worker visa (Fachkräfte): Recognised qualification and a job offer
  • Opportunity Card (Chancenkarte): Points-based job search for up to one year

Official routes: Make it in Germany (Federal Government portal)

Job description

About the role

Full text from the employer, as published on Arbeitnow, arranged into sections. Nothing added or removed.

01About Black Forest Labs

We're the team behind Latent Diffusion, Stable Diffusion, and FLUX-foundational technologies that changed how the world creates images and video. We're creating the generative models that power how people make images and video-tools used by millions of creators, developers, and businesses worldwide. Our FLUX models are among the most advanced in the world, and we're just getting started.

Headquartered in Freiburg, Germany with a growing presence in San Francisco, we're scaling fast while staying true to what makes us different: research excellence, open science, and building technology that expands human creativity.

02Why this role

FLUX models ship as open weights, which gives anyone full access to the model. Our safety efforts focus on suppressing harmful behaviors and mitigating the risk of misuse, so safety has to be built into the models themselves, not bolted on afterwards.

As a Member of Technical Staff on our safety research team, you'll research and ship methods that make FLUX models safe by design: from what goes into the training data to how the models are mid- and post-trained, across images, video and the text that conditions them. This is a role with real ownership: you won't just do research on model safety, you'll shape it. The methods you build ship in FLUX models with over 75 million downloads on Hugging Face and in production at some of the largest platforms in the world.

03What you'll work on

  • Develop mid- and post-training safety methods for FLUX models, such as safety SFT, preference optimization and RL with safety rewards, and concept erasure.

  • Build safety data filtering that runs at pretraining scale: classifiers and pipelines that screen billions of images, video clips and captions, with measured Pareto frontiers and precision/recall trade-offs.

  • Make safety hold up for open-weight releases, including robustness to adversarial prompts and to downstream fine-tuning.

  • Extend safety to the text side of the stack: prompts, captions and the text encoders that condition our models.

  • Design evaluations and red-teaming that measure harmful generations alongside image quality and prompt following, so safety gains don't come at the cost of performance.

  • Work directly with pretraining and post-training teams so your methods land in the release model, and publish where it makes sense.

04What we're looking for

  • Hands-on research experience in visual safety: safety of text-to-image, text-to-video or vision-language models, such as harm classifiers, safe generation methods or safety benchmarks.

  • Proven experience in at least one of:

    • Large-scale safety data filtering: building and running classifiers or filtering pipelines over hundreds of millions of samples or more.

    • Safety mid- or post-training: safety SFT, DPO or RL with safety objectives, or unlearning applied to large generative models.

  • Deep familiarity with concept erasure methods (e.g. ESD, UCE, adversarial unlearning) and their failure modes, such as concept recovery and collateral damage to unrelated concepts.

  • Track record of shipping: top-venue publications (NeurIPS, ICML, ICLR, CVPR, ICCV, ECCV) paired with production impact, or unambiguous production wins at a frontier lab.

  • Experience with distributed training at multi-node scale.

  • 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.

05We'd be especially excited if you

  • Know how to keep safety intact after release, when others fine-tune open weights.

  • Have tackled safety for video generation, where harm can emerge across frames rather than in any single frame.

  • Bring experience with audio safety, especially for jointly generated audio and video, where each modality can amplify harm in the other.

  • Have unlearned concepts from text encoders or built safety-tuned encoders (e.g. Safe-CLIP-style approaches).

  • Have worked on text safety: LLM safety tuning, prompt and jailbreak defenses, or text safety classifiers, ideally across languages.

  • Have applied latent-space safety methods, such as activation steering or safe guidance.

  • Have built VLM-based safety judges or guard models for filtering or evaluation.

06How we work together

We're a distributed team with real offices that people actually use. You'll join us in Freiburg at least 2 days a week (or one full week every other week). We'll cover reasonable travel costs to make this possible. We think in-person time matters, and we've structured things to make it accessible to all. We'll discuss what this will look like for the role during our interview process.

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.

07Compensation

EUR 160K-220K + equity, depending on profile

Find Jobs in Germany on Arbeitnow

CSI

Ask CSI about this job

Answers link to jobs and tools on Dev Global Jobs.

Get jobs like this

The best new matches, once a week. Free, one click to stop.

Community

Review Dev Global Jobs

Used this site to find a job? Tell other job seekers what worked and what did not.

Write a review on TrustpilotIt takes about two minutes↗