Senior Software Engineer - NIM Factory Container and Cloud Infrastructure
Core
Designing and implementing core container and cloud infrastructure strategies for NVIDIA Inference Microservices (NIMs) and hosted services, enabling reproducible, multi-arch, CUDA-optimized builds for enterprise-grade software.
Role type
Senior IC software engineer (container and cloud infrastructure)
Builds
Enterprise-grade container build, packaging, and deployment tooling for NIM runtimes and inference backends
Domain
AI infrastructure, GPU computing, cloud-native platforms
Deliverable
production ML models | infrastructure
Required skills
Python, Kubernetes, Docker/BuildKit, containerd/OCI, GPU workload management, CI/CD automation, Helm/Operator design, multi-cluster orchestration
Preferred skills
Helm chart design systems, Operators, platform APIs, inference backend knowledge (vLLM, SGLang, TRT-LLM), benchmarking inference performance, multi-tenant/edge container delivery, open-source contributions
Technologies
Python, Kubernetes, Docker, BuildKit, containerd, OCI, Helm, Operators, vLLM, SGLang, TRT-LLM, CUDA
Responsibilities
Design and harden containers for NIM runtimes; develop Python tooling for build orchestration and CI/CD; design Kubernetes deployment patterns with GPU scheduling and autoscaling; optimize container performance and resource utilization; evolve base image strategy and artifact registry topology; mentor teammates on engineering standards
Seniority
Senior, hands-on IC