Staff Test Engineer - AI SW Stack (9-13 years)

About the Role

Sandisk is seeking an experienced AI Software Stack Test Lead to define, drive, and execute validation strategy for a next-generation AI computational storage platform. This role owns end-to-end verification of the AI software stack, including neural network operators, compiler-generated workloads, runtime execution, memory management, scheduling systems, and model-level performance.

Key Responsibilities

• Validation Strategy & Technical Leadership: Own and define end-to-end validation strategy. Establish methodologies, coverage metrics, quality gates, and release-readiness criteria. Lead efforts across operator libraries, runtime systems, execution frameworks, and AI workloads.
• Mentorship: Mentor engineers and drive best practices for automation, performance validation, and debugging.
• Functional Validation: Validate neural network operators and compute kernels; verify graph-level execution and end-to-end model inference workflows against reference frameworks like PyTorch or TensorFlow. Ensure behavioral consistency across releases.
• Runtime & Execution Validation: Verify memory allocation and movement across host/device environments. Execute stress, concurrency, and multi-device scenarios.
• Performance & Scalability Validation: Design benchmarking frameworks for operator-level performance, model-level metrics (latency, throughput), time-to-first-token, and multi-device scaling efficiency.

Required Qualifications

• Experience: 10+ years in AI software validation, systems software validation, or related areas. The title specifies 9-13 years experience.
• Tech Stack: Strong C++ expertise; Object-Oriented Programming fundamentals; Advanced Python for automation and test infrastructure.
• Domain Knowledge: Deep understanding of AI/ML execution pipelines, neural network operators, deep learning frameworks (PyTorch preferred), runtime architectures, scheduling systems, parallel execution models, memory hierarchy, and DMA concepts.
• Certified Experience: Proven experience building automated test/benchmarking frameworks; strong debugging and root-cause analysis skills.

Preferred Qualifications

• Familiarity with MLIR, XLA, StableHLO, TVM, ONNX Runtime, TensorRT.
• Experience validating GPU, NPU, FPGA, or custom accelerator platforms.
• Proficiency with profiling tools: VTune, Nsight Systems, Nsight Compute, perf, gprof.
• Hands-on experience with distributed inference and multi-device execution.