Senior Site Reliability Engineer, Model Serving Infrastructure - Remote

Overview

The Senior Site Reliability Engineer will be responsible for developing, deploying, and operating the AI platform delivering Cohere's large language models through easy to use API endpoints. This role involves working with multiple teams to deploy optimized NLP models in low latency, high throughput, and high availability environments.

In Short

• Join a team focused on building high-performance, scalable AI systems.
• Work on deploying large language models via API endpoints.
• Collaborate with various teams to ensure smooth operations.
• Engage with customers for customized deployments.
• Focus on low latency and high availability for NLP applications.
• Contribute to the development of cutting-edge AI technologies.
• Be part of a diverse and inclusive work environment.
• Enjoy a range of employee benefits including health and wellness.
• Work remotely with flexible office options.
• Participate in a culture that values diversity and inclusion.

Requirements

• 5+ years of engineering experience in production infrastructure.
• Experience with Kubernetes and GPU workloads.
• Familiarity with cloud platforms like GCP, Azure, and AWS.
• Strong skills in Linux-based computing environments.
• Experience in resource and cost management.
• Excellent collaboration and troubleshooting skills.
• Ability to adapt and solve complex technical challenges.
• Knowledge of computational characteristics of accelerators.
• Strong understanding of distributed systems.
• Experience in high-performance programming languages like Golang or C++.

Benefits

• An open and inclusive culture and work environment.
• Work closely with a team at the cutting edge of AI research.
• Weekly lunch stipend, in-office lunches & snacks.
• Full health and dental benefits, including mental health support.
• 100% Parental Leave top-up for eligible employees.
• Personal enrichment benefits for various activities.
• Remote-flexible work environment with office options.
• 6 weeks of vacation.