Full-time

Lead Engineer for AI Model Infrastructure

Posted by Medium • toronto, on, Canada

📍 toronto, on 🕒 June 02, 2026

About the Role

Step into the role of Lead Engineer focusing on building AI model infrastructure. Harness GPU resources and create self-service platforms to enhance AI deployment capabilities.
As a Lead Engineer, your responsibilities include designing and operating GPU infrastructures tailored for diverse AI model use cases. You'll prioritize robust systems for model serving, while also implementing multi-model routing strategies. By spearheading initiatives on model optimization and self-service platforms, you will enhance team efficiency in deploying AI solutions.
Key Responsibilities:
• Design and manage GPU infrastructures for AI models
• Optimize model serving systems for latency and availability
• Drive comprehensive model lifecycle management
• Create self-service tools for developer teams
• Establish observability metrics for system performance
Requirements:
• 8+ years in software engineering
• Proven experience with ML infrastructure and cloud services
• Stro...

Ready to Apply?

Submit your application today and take the next step in your career journey with Medium.

Apply Now