Machine Learning Engineer - AI Safety
Black Forest LabsSan Francisco (United States)On-Site
Needs a free Superjobs account. You'll finish on Black Forest Labs's Ashby page.
Skill score
Summary
This ML engineer builds and improves a multilayered moderation stack of detection models that catch harmful, illegal, or copyright-infringing generated content. The role suits engineers who work across the full ML lifecycle, from experimentation to large-scale deployment, and who care about AI safety and integrity.
- Function
- Data Science
- Estimated salary
- Est. $120k–180k/yr
- Estimated for a mid-level role, ~3 yrs experience (typical for the level), United States. Not published by the employer.
- Work mode and location
- On-Site, San Francisco (United States)
- Employment type
- Full-time
Job description
Overview
Why This Role
Black Forest Labs’ products arm individuals with great creative power to produce novel media across a range of modalities. The quality of our models inevitably also gives bad actors the opportunity to create harmful, copyright-infringing, or illegal content.
In this role you will develop and improve our moderation system: a multilayered stack of detection models. Succeeding in this role requires creativity and familiarity with a large range of ML techniques. An effective solution that balances accuracy, cost, latency, and scalability will vary case-by-case, from classical ML fine-tuning, to RAG-based agents, to simple, lightweight semantic embeddings.
Our ideal candidate is able to work across the full stack of ML engineering, collaborate cross-functionally with many teams, including legal, policy, go-to market, and infra, and has a real interest in the domains of AI safety and integrity.
Roles and responsibilities
- Develop ML models and systems to detect harmful and/or illegal content across a variety of classes and modalities
- Collaborate with our core infrastructure team to integrate these models into a large-scale production serving pipeline
- Handle customer requests and feedback on our moderation behavior, and make quick adjustments in response
- Collaborate with our legal, policy, and product teams to design moderation policies that are technically feasible and effective while preserving a positive user experience
Skills required
Top skills
- VLM deployment
- multimodal classification
- open-source VLMs
- classification model tuning
All skills (10)
- eval set design
- precision/recall analysis
- drift monitoring
- ML engineering
- adversarial moderation
- safety classification
- VLM inference optimization
- classical ML
- copyright moderation
- child safety moderation
Qualifications
- Experience deploying VLMs at scale for the classification of multimodal content
- Experience building AI systems around state-of-the-art open-source VLMs
- Experience tuning models for classification tasks, including building eval sets, reasoning about precision/recall at threshold, and monitoring for drift
- Comfort with the full stack of ML engineering: from research and experimentation to large-scale deployment
Nice to have
- Comfort with the adversarial nature of generative AI moderation: prompt obfuscation, jailbreaks, output laundering, and evasion generally
- Experience in moderation/safety space, preferably across a range of modalities (text, image, video, audio)
- Experience optimizing VLM inference latency at scale
- Experience with non-VLM solutions for safety classification (e.g., classical ML)
- Domain knowledge and experience with content copyright and/or child safety moderation systems
Other details
How We Work Together
We’re a distributed team with real offices that people actually use. This role is based in San Francisco, and you’ll join us in the office at least 2 days a week, or one full week every other week.
Compensation
US $220,000 - $280,000 USD + Equity
Company info
About Black Forest Labs
Black Forest Labs builds generative AI models for visual intelligence, including the FLUX image generation model. Its technology is used by individual artists and enterprise applications to create images.