Sr. Engineer, Kernel Development and Optimization
Core
Developing performance-critical kernels for AI compute hardware to unlock capabilities across ML and HPC workloads.
Role type
Senior IC kernel development and optimization engineer
Builds
High-performance RISC-V CPU-based AI platforms
Domain
AI hardware / Semiconductor / High Performance Computing
Deliverable
production ML models
Required skills
C++ systems programming, low-level software development, concurrency and synchronization, latency hiding, compute vs memory trade-off analysis, profiling and benchmarking, complex debugging, performance problem decomposition
Preferred skills
GPU-style kernel design, matrix multiplication and attention primitives, host-side orchestration, parallelization strategies, micro-benchmarking, tooling development
Technologies
RISC-V, C++, CUDA (ecosystem context)
Responsibilities
Design and optimize GPU-style kernels for matrix multiplication, attention, and data movement; identify bottlenecks and deliver throughput improvements; contribute to host-side orchestration and parallelization; develop micro-benchmarks and regression tests; collaborate with compiler, runtime, ML, and hardware teams
Seniority
Senior, hands-on IC
