AI Infrastructure Engineer (GPU)

Location: Hybrid work model in the United States, with on-site locations in Santa Clara and Folsom, California; Hillsboro, Oregon; or Austin, Texas.

Annual salary: $170,500–$315,490 USD.

Company

hirify.global develops semiconductor technologies, processors, GPUs, and platforms for computing and artificial hirify.globalligence.

What you will do

• Own end-to-end performance optimization for state-of-the-art LLM inference on hirify.global GPUs.
• Profile, diagnose, and resolve bottlenecks across the inference and systems stack.
• Design and optimize custom GPU kernels for attention, mixture-of-experts, quantization, and operator fusion.
• Upstream hardware backends and architectural improvements to vLLM, SGLang, PyTorch, and related open-source projects.
• Apply roofline analysis and systematic profiling to guide GPU architecture and compiler roadmaps.
• Collaborate with architecture, compiler, hardware, and open-source engineering teams.

Requirements

• Bachelor’s degree in computer science, software engineering, artificial hirify.globalligence, machine learning, or a related field with 4+ years of experience; alternatively, a master’s degree with 3+ years or a PhD.
• At least 3 years of relevant software engineering experience in GPU computing, AI systems, or high-performance computing.
• Strong proficiency in modern C++ and Python, including the ability to modify complex systems-level code.
• Understanding of CPU/GPU architecture and modern LLM inference concepts, including attention, KV caching, continuous batching, speculative decoding, and prefill-decode disaggregation.
• Hands-on experience with custom GPU kernels and technologies such as Triton, SYCL, CUDA, CUTLASS, or comparable domain-specific languages.
• Ability to work in the United States under the stated hybrid work model.

Nice to have

• Open-source contributions to vLLM, SGLang, PyTorch, llama.cpp, or other inference engines.
• Experience with scale-out inference orchestration across multi-node topologies.
• Experience using AI coding agents to accelerate development and benchmark generation.

Culture & Benefits

• Hybrid schedule combining on-site work at an assigned hirify.global site with off-site work.
• Competitive compensation with stock bonuses.
• Health, retirement, and vacation benefits.
• Focus on advancing AI infrastructure and hirify.global GPU technology.