About this role
Role Purpose: The Sr. SW Test Engineer - Neural Library will be responsible for validating neural network operators and libraries for a next-generation AI computational storage product. The role focuses on ensuring the correctness, performance, and robustness of compute kernels deployed on advanced hardware platforms. Key Responsibilities: Validate neural network operators such as matmul, convolution, and attention using reference models. Develop automated tests for operator-level and graph-level validation. Perform numerical accuracy validation against frameworks like PyTorch or TensorFlow. Execute and maintain smoke and regression test suites. Benchmark and validate performance metrics including throughput, latency, and scaling behavior. Build and maintain performance benchmarking frameworks. Perform software profiling to analyze execution bottlenecks and conduct memory usage analysis to detect leaks. Identify issues across the compiler, runtime, and kernel execution stack. Debug failures across compute kernels, runtime APIs, and hardware execution. Collaborate with compiler, runtime, and hardware teams. Required Qualifications: 5 years of experience (based on the 5-8 years requirement) in AI/ML systems validation or performance testing. Strong C++ programming skills and Object-Oriented Programming (OOP) fundamentals. Experience with Python for test automation. Strong understanding of deep learning operators and frameworks, with a preference for PyTorch. Experience with numerical validation and floating-point behavior. Knowledge of parallel execution, memory hierarchy, and compute kernels. Preferred Qualifications: Experience with profiling and debugging tools such as perf, VTune, or Nsight. Experience with ML execution stacks like MLIR or XLA. Exposure to accelerator validation (GPU/NPU/FPGA) and experience validating large language model workloads.