Work on the Triton compiler and runtime stack for AMD CDNA architecture and AMD Instinct accelerators.
Originally posted November 11, 2026 by the employer.
About the role
In this role, you will advance the Triton compiler and runtime stack for AMD CDNA and GPU architectures by building native distributed execution and communication capabilities. You will develop compiler and runtime infrastructure that enables inter-GPU communication, scalable execution, and hardware utilization on AMD Instinct accelerators.
What you'll do
- Design and develop native distributed communication and execution capabilities within the Triton AMDGPU backend, enabling multi-GPU execution for large-scale AI workloads.
- Design and implement Triton compiler and runtime mechanisms for native GPU-initiated communication, including collective operations, remote memory access, synchronization, and distributed execution primitives.
- Drive performance optimization across compute and communication, including inter-GPU data movement, communication/computation overlap, memory hierarchy utilization, and GPU-driven scheduling efficiency.
- Develop and optimize distributed Triton kernels and execution models to achieve scalability and hardware utilization for AI workloads.
- Analyze, profile, and debug cross-stack issues spanning the Triton compiler, runtime, ROCm stack, and GPU hardware execution.
- Contribute to the open-source Triton and ROCm distributed ecosystem.
What you'll need
- Bachelor’s or Master's Degree in Computer Engineering, Computer Science, Electrical Engineering, or equivalent practical experience.
- Experience across compiler development, GPU software, distributed systems, or performance engineering.
- Understanding of modern GPU architectures, including execution model, memory hierarchy (LDS, L2, HBM), scheduling, occupancy, and hardware performance characteristics.
- Experience with GPU programming using Triton, HIP, CUDA, or similar parallel programming environments.
- Knowledge of MLIR and/or LLVM internals.
- Understanding of GPU runtime systems, communication stacks, and multi-GPU interconnects such as XGMI, NVLink, PCIe, or InfiniBand.
Nice to have
- Familiarity or hands-on experience with the Triton compiler and runtime.
- Familiarity with distributed GPU communication libraries such as RCCL, NCCL, NVSHMEM, rocSHMEM, or MPI.
- Experience developing, optimizing, and scaling workloads across multiple GPUs, including inter-GPU communication, synchronization, and communication/computation overlap.
- Experience profiling, debugging, and optimizing performance across compiler, runtime, and hardware layers.
- Familiarity with ROCm, HIP, CUDA, or similar GPU programming ecosystems, including performance profiling and optimization tools.
- Experience contributing to open-source projects.
Skills: Triton, ROCm, GPU architecture, multi-GPU, compiler, MLIR
More semiconductor jobs: AMD jobs
First seen in our index 5 days ago, well below the 47-day median for Infrastructure/Platform Software roles.
Infrastructure/Platform Software · GPU Software Stack
|
Open roles in category
338
|
Median days since first seen
47 d
|
Category median salary (all employers)
$220k
|
See the full market breakdown ▾Category comparison, skills in demand, and who else is hiring
| Metric | AMD | All employers we track in this specialty (338 roles · 24 employers) |
|---|---|---|
| Open roles in this specialty | 74 | 338 |
| Open roles in the wider Software, Firmware & Systems family | 381 | 6787 · 180 employers |
| Median days since first seen | 22 d | 47 d (+25 d vs this employer) |
| Median salary (USD postings) | n/a | $220k |
Skills observed across this category: Triton, ROCm, GPU architecture, multi-GPU, compiler, MLIR
Who's hiring in this category
- NVIDIA · 167 open roles · median 75 d
- AMD (this employer) · 74 open roles · median 26 d
- Intel Corporation · 29 open roles · median 27 d
- Qualcomm · 25 open roles · median 68 d
- Arm Holdings · 10 open roles · median 19 d
- Ampere Computing · 5 open roles · median 14 d
How we counted: 338 open Infrastructure/Platform Software (GPU Software Stack) roles from 24 employers tracked in the SemiconductorJobs index, counted 16 Nov 2026. Specialty figures count only roles carrying this exact specialty label, so an employer's related work in neighbouring specialties is not included there, and is counted in the wider Software, Firmware & Systems family row. Days are counted from when our index first saw each posting, not from the employer's original posting date.