Raydar
Staff Infrastructure Engineer
$350K–$450K
San Francisco, California · Staff · Full-time · Posted Oct 26, 2026
- Experience
- At least 5 years of infrastructure engineering experience.
About the job
Own and scale the production infrastructure and reliability of a model-serving platform across public clouds and GPU providers.
What you'll do
- Build and operate highly available Kubernetes clusters across public clouds and GPU providers.
- Troubleshoot the production serving stack, including GPU systems, and extend deployment tooling across accelerator types.
- Build monitoring, alerting, automated failover, self-healing systems, and traffic routing; partner with optimization engineers to validate performance under live traffic.
What they ask for
- Currently at staff level or above in an individual-contributor infrastructure role.
- Direct, hands-on experience running inference infrastructure day to day.
- Deep production Kubernetes experience at scale across AWS and GCP.
- Hands-on GPU debugging, LLM serving frameworks, high-performance cluster networking, and observability and reliability for latency-sensitive services.
Nice to have
- Experience deploying across mixed accelerator types.
- Contributions to open-source inference frameworks or a background on a production-scale inference platform.
Pay
USD 350,000 to 450,000 (base salary)
Tools
Kubernetes, AWS, GCP, CUDA
AI focus
Operate and improve production LLM/model-serving infrastructure, including inference performance, GPU troubleshooting, deployment, and reliability.
Model-written summary · the original posting is authoritative