Site Reliability Engineer at Cohere

Cohere is seeking a Site Reliability Engineer to enhance AI platform performance. Contribute to deploying robust machine learning systems in a remote-friendly environment.

As part of the Model Serving team at Cohere, you will develop and operate a platform for large language model API endpoints. This role requires collaborating with various teams to ensure efficient deployment and optimized performance in high-availability environments. You’ll engage with customers to tailor specific deployments that meet their needs, marking a significant impact in AI technology.

Key Responsibilities:

• Build self-service systems for managing services

• Automate Kubernetes deployments for language models

• Ensure environment observability and resilience

• Participate in on-call rotation for SLO adherence

• Foster relationships with internal teams for feedback integration

Requirements:

• 5+ years in production infrastructure engineering

• Experience with Kubernetes and large distributed systems

• Background in GCP, Azure, AWS, or similar

• Excellent troubleshooting and collaboration skills

• Familiarity with GPUs and distributed system technologies

Drive infrastructure excellence and build impactful AI systems as a Site Reliability Engineer at Cohere.
#J-18808-Ljbffr