Infrastructure - Deployment Lead – Real-Time ML Systems Offline

Job Description

We’re building the core systems behind some of the most dynamic digital character technology out there—and we need someone to take ownership of the platform that makes it all run. In this role, you’ll lead the development of infrastructure that ensures fast, scalable, and reliable machine learning services across a range of interactive applications. This is an opportunity to build systems that replicate the complexity of human movement and emotion in real time. You’ll work on challenging problems that bridge the physical and digital worlds—and contribute to experiences that feel truly alive.

🛠 Desired Skills and Experience

• 7+ years of experience in DevOps, ML engineering, or infrastructure leadership
• Strong track record with cloud architecture, containers, and deployment pipelines
• Expertise in serving ML models in production environments
• Familiarity with building for real-time performance constraints
• Bonus: background in simulation, graphics, or related real-time pipelines
  
  🎯 Responsibilities
   
• Architect scalable systems to support ML model training, deployment, and inference
• Streamline development workflows through CI/CD automation
• Optimize infrastructure for high-throughput, low-latency applications
• Develop observability tools to track system and model performance
• Enable engineers and researchers with reliable, developer-friendly tools and APIs