AI infrastructure engineers

RadixArk is launching a full-time, paid, 1-year residency program for aspiring AI infrastructure engineers. You’ll rotate across inference, training, kernels, compilers, and cluster infrastructure, working on real production systems alongside senior engineers. This is an opportunity to learn from the team behind SGLang and Miles while owning meaningful projects that impact thousands of developers., * 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

• Bachelor’s or Master’s degree in Computer Science, Engineering, or related field (recent graduates welcome)
• Strong foundations in systems programming, ML systems, or high-performance computing
• Experience with Python and/or C++; exposure to CUDA, JAX, or distributed systems is a plus
• Demonstrated ability to learn quickly and debug complex technical problems
• Curiosity, grit, and willingness to dive deep into unfamiliar layers of the stack
• Desire to grow into a world-class AI infrastructure engineer
• Strong communication skills and ability to work collaboratively

We offer competitive compensation with equity, comprehensive health benefits, and flexible work arrangements. Compensation is determined by location, level, and experience.

RadixArk is an infrastructure-first company built by engineers who’ve shipped production AI systems, created SGLang (30K+ GitHub stars, the fastest open LLM serving engine), and developed Miles (our large-scale RL framework). Founded by AI infrastructure veterans from xAI and NVIDIA, we’re on a mission to democratize frontier-level AI infrastructure by building world-class open systems for inference and training. Our team has optimized kernels serving billions of tokens daily, designed distributed training systems coordinating 10,000+ GPUs, and contributed to infrastructure that powers leading AI companies and research labs.