Senior Software Engineer

Run:ai, now part of NVIDIA, is looking for a Senior Software Engineer to build infrastructure that helps AI workloads start faster and run efficiently at scale.

You’ll work with Python, Go, Kubernetes, and distributed systems, and help lead an open-source project.

Responsibilities

• Develop scalable services, APIs, and libraries for managing and loading AI models and data.
• Integrate cloud infrastructure, storage, and AI frameworks in Kubernetes environments.
• Help guide an open-source project’s technical direction, review contributions, and coordinate releases with the community.
• Deliver features from design through production, improving performance and reliability through testing, monitoring, and benchmarking.
• Collaborate with engineers and product managers, contribute to technical decisions, and share knowledge.

Requirements

• A relevant degree or equivalent practical experience.
• At least 5 years of experience developing backend services, infrastructure, or developer tools.
• Proficiency in Python, Go, or another relevant language, with a willingness to learn new technologies.
• Hands-on experience with Kubernetes, containers, and Linux.
• Understanding of distributed systems and infrastructure fundamentals, including compute, networking, and storage.
• Experience delivering and supporting reliable production software.
• Regular use of AI tools for design, coding, testing, and debugging, with careful evaluation of generated outputs for correctness, security, and maintainability.
• Ability to investigate problems, explain technical tradeoffs, and collaborate across teams.

Nice to Have

• Experience with AI model loading, inference, or frameworks such as PyTorch, vLLM, or SGLang.
• Experience with cloud storage, caching, or performance optimization.
• Experience maintaining open-source projects or developing libraries and SDKs for other engineers.
• Familiarity with C++ or GPU computing.