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 a strong candidate to join us in developing and improving our API / model serving backend and services.

Role:

• Develop and maintain robust APIs for serving machine learning models
• Transform research models into production-ready demos and MVPs
• Optimize model inference for improved performance and scalability
• Implement and manage user preference data acquisition systems
• Ensure high availability and reliability of model serving infrastructure
• Collaborate with ML researchers to rapidly prototype and deploy new models

Ideal Experience:

• Strong proficiency in Python and its ecosystem for machine learning, data analysis, and web development
• Extensive experience with RESTful API development and deployment for ML tasks
• Familiarity with containerization and orchestration technologies (e.g., Docker, Kubernetes)
• Knowledge of cloud platforms (AWS, GCP, or Azure) for deploying and scaling ML services
• Proven track record in rapid ML model prototyping using tools like Streamlit or Gradio
• Experience with distributed task queues and scalable model serving architectures
• Understanding of monitoring, logging, and observability best practices for ML systems

Nice to have:

• Experience with frontend development frameworks (e.g., Vue.js, Angular, React)
• Familiarity with MLOps practices and tools
• Knowledge of database systems and data streaming technologies
• Experience with A/B testing and feature flagging in production environments
• Understanding of security best practices for API development and ML model serving
• Experience with real-time inference systems and low-latency optimizations
• Knowledge of CI/CD pipelines and automated testing for ML systems
• Expertise in ML inference optimizations, including techniques such as:
• Reducing initialization time and memory requirements
• Implementing dynamic batching
• Utilizing reduced precision and weight quantization
• Applying TensorRT optimizations
• Performing layer fusion and model compilation
• Writing custom CUDA code for performance enhancements