Specialty
The role
Cohere, an enterprise AI company, is hiring a Site Reliability Engineer for its Model Serving team, which runs the platform delivering its language models through APIs. The role is remote-friendly, with offices in several cities.
What you will do
- Build self-service systems to manage, deploy and operate services, including custom Kubernetes operators for model deployments.
- Automate observability and resilience so developers can troubleshoot problems themselves.
- Meet defined SLOs, including taking part in an on-call rotation.
- Gather feedback from internal developers to influence the Infrastructure team's roadmap.
- Share knowledge and review others' work.
What they ask for
- 5+ years running production infrastructure at large scale.
- Experience designing highly available distributed systems with Kubernetes, including GPU workloads.
- Experience with GCP, Azure, AWS, OCI or multi-cloud and hybrid serving.
- Experience supporting complex Linux-based environments and managing compute, storage, network and cost.
- Familiarity with how GPUs, TPUs or other accelerators affect inference latency and throughput.
- Experience in Go, C++ or another high-performance server language.
What they offer
- Weekly lunch stipend
- Health and dental benefits with a mental health budget
- RRSP matching, 401(k) or pension
- Parental leave top-up for up to 6 months
- 6 weeks paid vacation
- $500 home office stipend and co-working benefit
This is our own short reading of the posting. The full description, and anything that has changed since, is on Cohere's careers page behind the apply button.
