AI Software Development Engineer (Neuromorphic Computing)

Location: Santa Clara, California, United States. Hybrid work model with time split between the assigned Intel site and off-site work.

Annual salary: $170,500–$240,710 USD, with individual pay based on work location, skills, experience, and education.

Company

Intel's CTO Office is developing and commercializing neuromorphic computing technology for physical AI systems, including robots and intelligent edge devices.

What you will do

• Design and implement specialized AI kernels for current and next-generation neuromorphic hardware using custom DSLs and accelerator programming models.
• Optimize convolutional networks, transformers, and generative AI workloads through tiling, fusion, vectorization, parallelization, layout transformation, buffering, sparsity, and quantization.
• Develop performance methodologies covering compute utilization, latency, throughput, memory bandwidth, data movement, synchronization, and scaling.
• Build reference models, numerical validation tools, benchmarks, and performance, power, and area models for hardware-software co-design.
• Validate results across models, simulators, emulators, and hardware while contributing to maintainable code, tests, documentation, and performance-regression infrastructure.
• Collaborate with hardware architects, compiler engineers, AI researchers, runtime engineers, and application teams across the hardware-software lifecycle.

Requirements

• PhD with no prior professional experience, master's degree with 2+ years of relevant experience, or bachelor's degree with 4+ years of relevant experience in a related technical field.
• 4+ years of experience developing, debugging, and delivering maintainable software in Python and either C or C++, including performance-critical or systems-level code.
• 2+ years of experience implementing and optimizing numerical, machine-learning, or high-performance computing kernels using parallel programming and CUDA, SYCL, OpenCL, Triton, or a comparable technology.
• 2+ years of experience developing, training, or evaluating AI algorithms and machine-learning models with PyTorch, JAX, TensorFlow, or a comparable framework.
• 2+ years of experience establishing numerical correctness and measuring performance through reference implementations, automated testing, benchmarking, profiling, or regression infrastructure.
• Hybrid work requires time at the assigned Intel site in Santa Clara, California.

Nice to have

• Experience with convolutional networks, transformers, generative AI, edge AI, or physical AI workloads.
• Experience with MLIR, LLVM, TVM, Triton, compiler technologies, or domain-specific language development.
• Experience with hardware performance modeling, architecture simulators, PPA analysis, or hardware-software co-design.
• Advanced optimization experience with kernel fusion, tiling, vectorization, quantization, sparsity, layout optimization, or double buffering.
• Experience with spatial, dataflow, neuromorphic, or other emerging AI accelerator architectures and collaborative software development practices.

Culture & Benefits

• Work in a vertically integrated incubation effort focused on bringing neuromorphic technology to market.
• Collaborate with a global ecosystem of research groups and multidisciplinary engineering teams.
• Health, retirement, and vacation benefits.
• Competitive pay and stock bonuses.
• Hybrid flexibility combining on-site and off-site work.