Sandisk
Technology
AISoftwareLead–PyTorch&CUDARuntime(Next-GenAccelerator)
Neural analysis suggests this role is
optimal for mid candidates.
“AI Software Lead – PyTorch & CUDA Runtime (Next-Gen Accelerator) at Sandisk. Skills: PyTorch, CUDA Runtime, NN Operators, AI Accelerators. Design NN operators. Optimize NN operators”
What You'll Achieve.
Efficient AI workload execution; Drive performance; Drive scalability; Drive hardware utilization
Industry & Context.
Performance bottleneck analysis
What They're Looking For.
Must Have
8+ years systems software, 8+ years runtime engineering, 8+ years performance engineering, PyTorch/TensorFlow/JAX experience, NN operator/kernel development, NN operator optimization, Operator fusion experience, Graph-level optimizations experience, C/C++ expertise, CUDA expertise, Runtime systems expertise, Execution engines expertise, Memory hierarchy understanding, Data movement understanding, Parallel execution understanding
Nice to Have
GPU/NPU accelerator experience, Custom AI accelerator experience, XLA familiarity, MLIR familiarity, Compiler-runtime interaction familiarity, LLM optimization experience, Large-scale DL optimization experience
What You'll Do.
Optimize NN operators
Drive runtime optimizations
Own runtime interfaces
Implement operator fusion
Optimize operator fusion
Identify performance bottlenecks
Resolve performance bottlenecks
How You'll Work.
Team & Collaboration
Compiler teams; PyTorch framework teams; Low-level SW teams
Full Job Description
Sandisk understands how people and businesses consume data and we relentlessly innovate to deliver solutions that enable today’s needs and tomorrow’s next big ideas. With a rich history of groundbreaking innovations in Flash and advanced memory technologies, our solutions have become the beating heart of the digital world we’re living in and that we have the power to shape. Sandisk meets people and businesses at the intersection of their aspirations and the moment, enabling them to keep moving and pushing possibility forward. We do this through the balance of our powerhouse manufacturing capabilities and our industry-leading portfolio of products that are recognized globally for innovation, performance and quality. Sandisk has two facilities recognized by the World Economic Forum as part of the Global Lighthouse Network for advanced 4IR innovations. These facilities were also recognized as Sustainability Lighthouses for breakthroughs in efficient operations. With our global reach, we ensure the global supply chain has access to the Flash memory it needs to keep our world moving forward. Role Overview We are looking for a Software Lead (8+ years’ experience) to own the runtime and neural network (NN) layer of a next-generation AI accelerator platform. This role focuses on designing, optimizing, and implementing NN operators and developing new ops using CUDA/custom runtime APIs to deliver high-performance execution on custom AI hardware. Key Responsibilities * Design and optimize NN operators for performance-critical workloads * Develop new NN ops using CUDA/custom runtime APIs * Drive runtime-level optimizations across compute, memory, and scheduling * Own runtime ↔ NN layer interfaces and execution model * Implement and optimize operator fusion (e.g., matmul + bias + LayerNorm) for efficient hardware utilization * Identify and resolve performance bottlenecks across the stack * Collaborate with compiler, PyTorch framework, and low-level SW teams Impact * Own how effi
Applying for this AI Software Lead – PyTorch & CUDA Runtime (Next-Gen Accelerator) role?
Most applicants get filtered before a human reads their resume. See if yours makes the cut.
How to Apply on SmartRecruiters
- SmartRecruiters often includes a video screening step — check camera and mic permissions.
- Link your GitHub or portfolio directly in the profile section for technical roles.
- Applications may be reviewed by AI scoring before reaching a recruiter — use keywords from the job description.
ANONYMOUS · UNFILTERED
What do employees actually say about Sandisk?
Real rants from real employees. Read before you apply.