16 days ago
Bengaluru, IndiaSenior
Responsibilities
- Validate neural network operators and libraries for correctness, performance, and robustness.
- Develop automated tests for operator-level and graph-level validation.
- Perform numerical accuracy validation against reference frameworks such as PyTorch and TensorFlow.
- Execute and maintain smoke and regression test suites.
- Build benchmarking frameworks and validate throughput, latency, and scaling behavior.
- Profile software, analyze execution bottlenecks, and conduct memory usage and leak analysis.
- Debug failures across compute kernels, runtime APIs, and hardware execution.
- Collaborate with compiler, runtime, and hardware teams.
Requirements
- 4–6 years of experience in AI/ML systems validation or performance testing.
- Strong C++ programming skills and object-oriented programming fundamentals are mandatory.
- Experience with Python for test automation.
- Strong understanding of deep learning operators and frameworks, with PyTorch preferred.
- Experience with numerical validation and floating-point behavior.
- Knowledge of parallel execution, memory hierarchy, and compute kernels.
- Preferred experience with profiling and debugging tools including perf, VTune, and Nsight.
- Preferred experience with ML execution stacks such as MLIR or XLA.
- Exposure to GPU, NPU, or FPGA accelerator validation.
- Experience validating large language model workloads is preferred.