Cohere
Mid
Run and automate the Kubernetes-based platform serving Cohere's LLMs in production
Cohere's Model Serving team is hiring a Site Reliability Engineer to build self-service systems, custom Kubernetes operators, and observability tooling for the AI platform that serves Cohere's large language models via low-latency, high-throughput API endpoints. The role wants 5+ years running large-scale production infrastructure, deep Kubernetes and GPU-workload experience, multi-cloud exposure, and comfort with Golang/C++ for high-performance serving systems, based in Toronto with an on-call rotation.
Step into this interview
Free · a live voice mock calibrated to this exact role
What this interview tests
- Kubernetes operators and self-service infrastructure automation
- GPU/accelerator-aware scheduling and inference latency/throughput tradeoffs
- SLO definition, on-call ownership, and incident response
- Multi-cloud and hybrid/on-prem infrastructure experience
- Observability design for broad developer self-service debugging
- Systems programming in Golang or C++ for high-performance serving
Common question themes
Describe a Kubernetes operator or automation system you built and the toil it removed
How do GPU/accelerator characteristics change your approach to scheduling inference workloads
Walk through an SLO you owned that came under threat, and what you did
A time you worked across more than one cloud provider or a hybrid/on-prem setup
How you design observability so other developers can self-serve troubleshooting
A production incident during on-call and how you drove it to resolution
Related interviews
Cohere
Mid
Forward Deployed Engineer, Agentic Platform
Cohere
Mid
Member of Technical Staff, Applied ML
Cohere
Senior
Data Engineer, Data Foundations
Dropbox
Mid
Site Reliability Engineer
Coinbase
Senior
Senior Site Reliability Engineer, Core AI Infrastructure
GitLab
Mid