AI Infra Resident (1-Year Program)

RadixArk is launching a full-time, paid, 1-year residency program for aspiring AI infrastructure engineers. The role involves rotating across various domains such as inference and training, working on real production systems alongside senior engineers, and owning meaningful projects that impact thousands of developers.

Responsibilities:

• Join a full-time, paid, 1-year residency focused on AI infrastructure
• Rotate across inference, training, kernels, compilers, and cluster infrastructure
• Work on real production systems: LLM serving (SGLang), diffusion inference (Flux, Wan), RL training (Miles), schedulers, and performance tooling
• Learn to debug failures across the full stack: model → runtime → kernel → hardware
• Own meaningful projects with close mentorship from senior engineers
• Contribute to SGLang, Miles, and other open-source projects
• Document learnings and create guides for the community
• Present technical deep-dives and share knowledge with the team
• Participate in code reviews and learn engineering best practices