Position Details
About this role
This role involves designing and implementing container and cloud infrastructure for NVIDIA's AI inference microservices, focusing on performance, scalability, and reliability in GPU-accelerated environments.
Key Responsibilities
- Design and build containers for NIM runtimes
- Develop Python tooling for orchestration and CI/CD
- Optimize container performance and GPU utilization
- Evolve container image strategies and registry topology
- Collaborate across teams to ensure model availability
Technical Overview
The technical environment includes Kubernetes, Docker, containerd, OCI standards, Python tooling, Helm charts, NVIDIA GPU tools, and cloud services, with a focus on container orchestration, GPU workload optimization, and AI inference deployment.
Ideal Candidate
The ideal candidate is a highly experienced software engineer with over 10 years of expertise in containerization, Kubernetes, and GPU workloads, particularly in deploying AI inference microservices. They possess strong Python skills and deep knowledge of container build and deployment strategies for high-performance environments.
Must-Have Skills
Nice-to-Have Skills
Tools & Platforms
Required Skills
Hard Skills
Soft Skills
Industry & Role
Keywords for Your Resume
Deal Breakers
Less than 10 years of experience in software engineering, Lack of Kubernetes or container experience, No experience with GPU workloads or NVIDIA tools, No proficiency in Python, No experience with container image layering or registry workflows
Get matched to jobs like this
Luna finds roles that fit your skills and career goals — no endless scrolling required.
Create a Free Profile