AI Infrastructure Engineer

About Teton: Teton builds scalable AI systems for healthcare applications, combining technical expertise with domain knowledge to deliver impactful solutions. Our infrastructure team ensures reliable deployment of complex AI models.

Role Overview: As an AI Infrastructure Engineer at Teton, you’ll design and maintain the systems that power our AI capabilities. You’ll ensure our models deploy reliably at scale while optimizing performance and cost.

Key Responsibilities:

• Design and implement scalable ML infrastructure
• Optimize model deployment pipelines
• Develop monitoring and maintenance systems
• Collaborate with research and engineering teams
• Implement CI/CD for machine learning workflows
• Ensure system reliability and performance

Required Skills:

• Experience with ML infrastructure (TensorFlow Serving, TorchServe)
• Knowledge of containerization (Docker, Kubernetes)
• Cloud platform expertise (AWS/Azure/GCP)
• Proficiency in Python and infrastructure automation
• Understanding of distributed systems

Ideal Candidate:

• 5+ years of experience in ML infrastructure
• Strong background in distributed systems
• Experience with MLOps tools and practices
• Cloud computing certifications preferred
• Ability to balance technical depth with architectural vision
• Excellent problem-solving skills with a focus on reliability