Design and implement custom ML kernels (CUDA, CuTe, Triton) for core dLLM operations such as attention, matrix multiplication, gating, and normalization, optimized for modern GPU architectures.
Design compute primitives to reduce memory bandwidth bottlenecks and improve kernel efficiency.
Software engineering fundamentals: This is a software engineering role with a security specialization. Expect to spend 70%+ of your time writing code, building security tools, and automating security best practices. You'll need strong command of CS fundamentals, to design, build, and maintain secure software systems.
