Black Forest Labs is a cutting-edge startup pioneering generative image and video models. Our team, which invented Stable Diffusion, Stable Video Diffusion, and FLUX.1, is currently seeking a strong researcher / engineer to work closely with our research team on benchmarking and inference optimisation.
The Role:
- Benchmark our generative models against the current state-of-the-art (SOTA) across a range of tasks and datasets
- Identify strengths, weaknesses, and blind spots in model behavior and performance
- Explore and implement techniques to optimize inference performance, including speed, accuracy, and resource efficiency
- Stay up-to-date with the latest research in generative AI and contribute to internal knowledge-sharing
- Collaborate with the engineering and product teams to bring research insights into practical deployment
- Contribute to open-source efforts or publish findings, depending on interest
Required Qualifications:
- Hands-on experience evaluating generative models (experience with diffusion models is a strong plus)
- Solid understanding of deep learning fundamentals and model evaluation techniques
- Strong programming skills in Python; familiarity with ML frameworks such as PyTorch.
Preferred Qualifications:
- Previous internship or research experience in generative AI or computer vision
- Demonstrated interest in the field (e.g., GitHub projects, open-source contributions, personal research)
- Familiarity with current SOTA benchmarks and relevant datasets in generative modeling
- MS or PhD in Machine Learning, Computer Vision, Artificial Intelligence, or a related field
