Compiler Engineer - PyTorch + Kernel DSLPLATE

About the Company

Our technology solutions power the tools you use every day—smartphones, electric vehicles, hyperscale data centers, IoT devices, and so much more. Here you’ll have the opportunity to join a global leader whose innovative designs push the boundaries of possibility and shape the future.

We believe innovation and growth are driven by an inclusive culture and a diverse workforce. We’re dedicated to empowering people to be their true selves, building a better tomorrow for employees, customers, partners, and communities.

Daily onsite presence at our San Jose, CA office / U.S. headquarters in alignment with our Flexible Work policy.

• Adapt torch.compile to our backend: lower Inductor’s IR to our hardware, define fusions, specializations, and determine where the compiler should yield to hand‑written kernels.
• Build or extend kernel DSLs for our hardware: employ a tile‑based programming model (Triton‑style), higher‑level expressions (Helion‑style), or a custom DSL, and lower it to our ISA, memory hierarchy, and collective primitives.
• Design placement and scheduling passes: given a graph and our distributed memory model, decide where tensors live, when to migrate them, and how to overlap compute with data movement.
• Implement parallelism‑aware lowering: make tensor, pipeline, expert, and sequence parallelism first‑class in the compiler IR.
• Handle fusion, tiling, and memory planning: tackle classic compiler problems for a non‑uniform memory hierarchy where tile size and placement are coupled decisions.
• Contribute upstream: when using open‑source DSLs, ensure our work lands upstream (PyTorch, Triton, Helion, LLVM/MLIR, etc.) rather than remaining in a private fork.

• Bachelor’s with 10+ years, or Master’s with 8+ years, or PhD with 5+ years of industry experience.
• 3–5+ years of industry experience in at least one of:
  Triton, Helion, MLIR, XLA, TVM, Inductor, IREE, CUTLASS, or a proprietary equivalent.
• Experience designing a kernel DSL or its IR from scratch, or making non‑trivial language‑level changes to an existing DSL.
• Experience with MLIR—writing dialects, passes, or backend integration.
• Experience building PyTorch backends for non‑CUDA accelerators (XPU, ROCm, MPS, TPU, custom).
• Experience with kernel autotuning, performance modeling, or cost‑based compilation.
• Background in HPC, distributed systems, or NUMA‑aware programming—anything that builds intuition for non‑flat memory.
• Open‑source contributions to PyTorch, Triton, Helion, LLVM/MLIR, or similar projects is a big plus.

• Give Back: A charitable giving match and frequent opportunities to get involved.
• Enjoy Time Away: 4+ weeks paid time off a year, plus holidays and sick leave.
• Care for Family:
  Stipends for fertility care or adoption, medical travel support, and virtual vet care for your fur babies.
• Prioritize Emotional Wellness:
  On‑demand apps and free confidential therapy sessions.
• Stay Fit:
  Onsite café and gym, plus virtual classes to keep active.
• Embrace Flexibility:
  Flexible environment to find the right balance for you.

$163,000 – $253,000 USD

Samsung Semiconductor takes pride in being an equal opportunity workplace dedicated to fostering an environment where all individuals feel valued and empowered to excel, regardless of race, religion, color, age, disability, sex, gender identity, sexual orientation, ancestry, genetic information, marital status, national origin, political affiliation, or veteran status.

When selecting team members, we prioritize talent and qualities such as humility, kindness, and dedication. We extend comprehensive accommodations throughout our recruiting processes for candidates with disabilities, long‑term conditions, neurodivergent individuals, or those requiring pregnancy‑related support. All candidates scheduled for an interview will receive guidance on requesting accommodations.

At Samsung Semiconductor, we use Artificial Intelligence (AI) tools in the recruitment process to enhance efficiency. However, AI is used as a support tool, not a final decision‑maker. All hiring decisions are made by our human recruiting team and hiring managers to ensure every candidate is evaluated fairly and holistically.

By submitting an application, you agree not to disclose to Samsung—or encourage Samsung to use—any confidential or proprietary information (including trade secrets) belonging to a current or former employer or other entity.