SRE: AI Inference Platform & ML Systems

Cohere; San Francisco (CA); Hybrid; USD 120,000 - 150,000; Full time

Benefits offered by this job

Open and inclusive culture

Weekly lunch stipend

Full health and dental benefits

100% Parental Leave top-up

Personal enrichment benefits

Remote-flexible work

6 weeks of vacation

Job summary

A leading AI technology company in San Francisco is looking for a Site Reliability Engineer to build high-performance, scalable systems for model serving. You will collaborate with teams to deploy optimized NLP models and ensure high availability. Ideal candidates have 5+ years of experience, particularly in Kubernetes and large-scale infrastructure. The role is focused on automating services and maintaining system reliability in a fast-paced environment. The company values diversity and provides competitive benefits including 6 weeks of vacation.

Qualifications

• 5+ years of engineering experience running production infrastructure at a large scale.
• Experience designing distributed systems with Kubernetes, and GPU workloads.
• Strong understanding of distributed systems.

Responsibilities

• Build self-service systems for deploying and managing services.
• Automate environment observability and resilience.
• Ensure defined SLOs are met, including on-call rotation.

Skills

Kubernetes

GCP

AWS

Collaboration

Troubleshooting

Golang

C++

Cloud Infrastructure

Job description

A leading AI technology company in San Francisco is looking for a Site Reliability Engineer to build high-performance, scalable systems for model serving. You will collaborate with teams to deploy optimized NLP models and ensure high availability. Ideal candidates have 5+ years of experience, particularly in Kubernetes and large-scale infrastructure. The role is focused on automating services and maintaining system reliability in a fast-paced environment. The company values diversity and provides competitive benefits including 6 weeks of vacation.