Software Engineer (Product, Infrastructure and Platform Reliability)

Highlights

• Own reliability and SLAs across Sakana AI products reaching production at scale.
• Improve latency, throughput and cost efficiency of production LLM inference.
• Turn world-class AI research into products used by real enterprise customers.

Ideal candidate

A reliability-minded infrastructure engineer who thrives owning production systems end-to-end and balancing latency, cost and operability. Comfortable in global bilingual teams and translating product and enterprise needs into dependable platforms.

Requirements

• Experience designing and operating production infrastructure in a cloud environment such as AWS or GCP
• Experience operating containerized services, APIs, batch jobs, or model inference workloads in production
• Experience managing and automating infrastructure with IaC or comparable tooling
• Hands-on experience with monitoring, alerting, incident response, and postmortems
• Ability to reason about GPU, cloud, and serving resource usage from cost, performance, and availability perspectives
• Experience with LLM serving frameworks such as vLLM, TensorRT-LLM, or SGLang
• English communication skills sufficient to drive technical projects with internal and external stakeholders
• Japanese language ability (JLPT N1/N2 if applicable)