Member of Technical Staff — Inference-Kernel, Compiler & Communication

RadixArk • Palo Alto, CA

22h

About The Position

RadixArk is seeking a deeply technical engineer to improve performance for frontier AI systems by working at the lowest layers of the stack, including kernels, runtimes, compilers, and communication libraries. The role focuses on extracting maximum efficiency from modern accelerators and interconnects and scaling training and inference across large GPU clusters, where microseconds and memory bandwidth matter. The work will shape the performance envelope of next-generation AI systems and involves solving challenging performance problems close to the hardware.

Requirements

• 5+ years of experience in systems, compiler, or performance engineering.
• Strong expertise in CUDA or accelerator programming.
• Deep understanding of GPU architecture and memory hierarchy.
• Experience writing or optimizing high-performance kernels.
• Strong background in compilers, runtimes, or code generation.
• Experience with distributed communication libraries such as NCCL, MPI, or RCCL.
• Solid knowledge of networking and interconnect technologies.
• Proficiency in C++ and Python.
• Strong system-level debugging and profiling skills.

Nice To Haves

• Experience with Triton, TVM, XLA, or MLIR.
• Experience building compiler passes or IR transformations.
• Familiarity with NVLink, InfiniBand, or RDMA.
• Experience optimizing collective communication at scale.
• Background in HPC or performance-critical systems.
• Contributions to open source kernel, compiler, or ML systems.
• Experience scaling workloads to 1,000+ GPUs.
• Experience with mixed-precision or quantized kernels.

Responsibilities

• Design and implement high-performance kernels for AI workloads.
• Optimize compiler and runtime stacks for machine-learning systems.
• Improve communication efficiency across large GPU clusters.
• Reduce latency and increase throughput for distributed workloads.
• Profile and eliminate system bottlenecks across the stack.
• Collaborate with training and inference teams on performance optimization.
• Develop tooling for profiling and performance analysis.
• Contribute to long-term architecture for performance-critical systems.
• Advance hardware–software co-design.

Benefits

• Equity

What This Job Offers

• Job Type: Full-time
• Career Level: Senior
• Education Level: No Education Listed