Software Engineer - Infrastructure
Core
Build and maintain core components of an ML inference platform to enable developers to deploy, scale, and monitor production AI applications with high performance.
Role type
Senior IC infrastructure software engineer (ML inference platform)
Builds
ML inference platform components, Kubernetes deployments, and orchestration layers for model serving
Domain
AI/ML infrastructure, cloud-native systems, distributed computing
Deliverable
production ML models
Required skills
Python, Go, Kubernetes, containerization, distributed systems concepts, monitoring and logging tools, resource management for ML workloads
Preferred skills
B200 GPU experience, H100 GPU experience, multi-cloud capacity management, fractional GPU allocation
Technologies
Python, Go, Kubernetes, B200 GPUs, H100 GPUs
Responsibilities
Develop infrastructure components for ML inference platform, implement and maintain Kubernetes deployments, contribute to inference orchestration layer, build monitoring systems for model performance, implement efficient resource management solutions, support infrastructure automation, balance performance optimization with system reliability
Seniority
Senior, hands-on IC