Overview
Build and optimize real-time diffusion models that power our interactive video platform, enabling users to make instant changes to video content. You’ll design scalable ML systems that run seamlessly in real-time, supporting image/video rendering and high-frequency user interactions.
Responsibilities
Develop and optimize ML models for real-time image and video generation, prioritizing responsiveness and scalability
Build and maintain ML pipelines for deploying models in edge and cloud environments (AWS), ensuring low-latency processing and high availability
Continuously research advancements in image/video diffusion, implementing improvements for performance, efficiency, and model accuracy
Qualifications
5+ years in ML/deep learning, with expertise in real-time image generation or generative models
Experience deploying high-performance models at scale in edge and cloud environments (e.g., AWS)
Strong foundation in computer vision and video processing, with a focus on low-latency optimization
Proficiency in Python, TensorFlow/PyTorch, and model deployment for interactive applications
BS, MS, or PhD in Computer Science or related field
Startup experience or background in developing consumer interactive media applications is a plus
What we offer
Competitive salary, meaningful equity, and a fast-paced, innovation-driven team culture.