What are the responsibilities and job description for the GPU Software Engineer position at Triune Infomatics Inc?
Role: GPU Software Engineer
Location: San Jose, CA – Onsite
Duration: 6 Months Contract-to-Hire
Overview: We’re looking for a strong GPU Software Engineer to join a high‑impact engineering team working on next‑generation AI, GPU, and semiconductor technologies. This role focuses on GPU kernel development, memory architecture, and integration with modern inference systems such as vLLM and SGLang. You’ll work onsite in San Jose, collaborating closely with a team of engineers building high‑performance GPU‑accelerated systems.
Essential Skills:
- GPU Architecture Expertise: In-depth understanding of GPU architectures, memory models (including HBM and P2P), and thread hierarchies.
- GPU Software Proficiency: End-to-end knowledge of AMD/Nvidia GPU software stacks.
- Programming Experience: Familiarity with programming models such as CUDA, ROCm/HIP, OpenCL, or MPI.
- Inference Server Experience: Hands-on experience with inference servers like vLLM and SGLang.
- Kernel Development: Experience developing CUDA/ROCm kernels.
- Performance Optimization: Proven ability to optimize performance.
Technical Proficiency:
- Programming Languages: Expert-level proficiency in C and Python.
- Deep Learning Frameworks: Experience with frameworks like PyTorch or TensorFlow is a plus.
Preferred Skills:
- Networking Technologies: Familiarity with RDMA/RoCE, InfiniBand, or Infinity Fabric is desirable.
Salary : $80 - $100