Site Reliability Engineer
Core
Design and operate reliable managed AI services, focusing on serving and scaling LLM workloads to ensure high availability and performance for compute-intensive tasks.
Role type
Staff Site Reliability Engineer (AI Infrastructure)
Builds
Managed AI services, distributed AI pipelines, inference services, and next-generation distributed systems for AI-first environments.
Domain
AI Infrastructure / Cloud Services / Distributed Systems
Deliverable
production ML models
Required skills
Distributed systems design, Large Language Models (LLMs) experience, Kubernetes expertise, Modern programming languages (Python, Go, Java, C++), SRE practices (SLIs/SLOs, observability, fault tolerance), Automation tooling, Telemetry and profiling.
Preferred skills
Experience scaling inference or training workloads for LLMs.
Technologies
Kubernetes, Python, Go, Java, C++, LLMs, AI/ML infrastructure.
Responsibilities
Design and operate reliable managed AI services, Build automation and reliability tooling for distributed AI pipelines, Define and improve SLIs/SLOs for AI workloads, Collaborate with AI and platform teams to optimize training and inference clusters, Automate observability with telemetry and performance tuning, Investigate and resolve reliability issues in distributed AI systems.
Seniority
Staff, hands-on IC
