Senior Software Engineer - AI Compute Libraries & Performance
Core
Build high-performance AI compute libraries for next-generation AI hardware, focusing on linear algebra, tensor operations, and low-level performance optimization.
Role type
Senior IC software engineer (AI compute kernels)
Builds
High-performance compute libraries (ML Kernels & Runtime) for AI hardware
Domain
Semiconductor / AI Infrastructure
Deliverable
production ML models
Required skills
C++, linear algebra, tensor operations, performance optimization, microbenchmarking, regression testing, numerical validation, threading, cache locality, memory layout, kernel launch efficiency, debugging
Technologies
C++
Responsibilities
Design and implement kernels for linear algebra and tensor ops (GEMM, batched GEMM, convolutions, reductions, elementwise and fused operations); Own performance and correctness by adding microbenchmarks, regression tests, and numerical validation; Profile and optimize for next-generation AI hardware (threading, cache locality, memory layout, kernel launch efficiency); Debug issues and improve product quality; Engage in Agile ways of working