Generative AI Inference Engineer

About the role

Stability AI is seeking passionate Machine Learning Engineers to join its Inference team focused on creative applications of generative AI models. As a Generative AI Inference Engineer, you will leverage cutting-edge technology to push the boundaries of multi-modal inference optimization.

Responsibilities

• Drive the design and development of multi-modal ML inference systems.
• Collaborate with Platform and Inference teams on model optimization and deployment.
• Partner with cloud providers to deliver hosted Stability AI inference solutions.
• Act as a strategic thought partner driving business impact through ML.
• Prototype and productionize enhancements and new inference features.

Qualifications

• 7+ years of experience productionizing machine learning systems.
• Expert in Python services at scale and scientific stack including pyTorch.
• Proficiency in at least one high-performance inference framework like Triton or TensorRT.
• Deep understanding of diffusion architectures and profiling tools for Nvidia GPUs.
• Experience with Kubernetes, major cloud providers (AWS, GCP, Azure), Docker and open-source ML ecosystems.
• Strong communication, collaboration, and documentation skills.

Key skills/competency

• Machine Learning
• Inference Systems
• Multi-modal Models
• Python
• pyTorch
• Docker
• Cloud Deployment
• Diffusion Architecture
• Optimization
• High-performance Computing

Equal Employment Opportunity

Stability AI is an equal opportunity employer and does not discriminate on the basis of race, religion, national origin, gender, sexual orientation, age, veteran status, disability or other legally protected statuses.