Member of Technical Staff — Developer Technology (AI)

Location: Palo Alto, CA, United States

Salary: $200,000–$400,000 USD annually, plus equity

Company

hirify.global is an infrastructure-first AI company building open systems for high-performance LLM inference and training, including SGLang and Miles.

What you will do

• Profile and optimize GPU performance for production AI workloads across current and next-generation hardware.
• Root-cause performance and correctness bottlenecks from GPU kernels through distributed multi-node systems.
• Specialize in inference performance, GPU kernels and model enablement, speculative decoding, or training systems.
• Build and optimize custom CUDA, ROCm, or Triton kernels and support new models on new hardware.
• Partner with expert engineering teams to turn ambiguous technical problems into measurable improvements, cookbooks, and recommendations.
• Feed user-driven improvements into the open-source SGLang and Miles systems and their future roadmap.

Requirements

• 4+ years of experience in GPU systems, LLM infrastructure, or performance engineering.
• Strong profiling, debugging, and performance root-cause analysis skills.
• Hands-on experience with at least one of CUDA, ROCm, or Triton, with willingness to work across platforms.
• Strong Python programming skills plus C++ or CUDA experience.
• Ability to make progress on difficult, ambiguous problems and ramp quickly into unfamiliar systems and codebases.
• Ability to translate ambiguous requests into clear technical plans, verified cookbooks, and actionable recommendations for expert engineering audiences.

Nice to have

• Experience with LLM inference internals, including distributed serving, parallelism, routing, KV-cache management, and scheduling.
• Experience with low-precision quantization such as FP8, INT8, or INT4, and custom GPU kernel optimization.
• Familiarity with speculative decoding, large-scale distributed training, elasticity, or long-context workloads.
• Experience optimizing across NVIDIA and AMD platforms.
• Experience with SGLang, Miles, vLLM, TensorRT-LLM, Megatron, or comparable frameworks, including open-source AI/ML contributions.

Culture & Benefits

• Work on open AI infrastructure intended to make frontier-level inference and training more accessible.
• Collaborate with leading AI companies, research labs, and expert engineering partners.
• Contribute to systems serving large-scale production workloads and distributed training environments.
• Equity is included in the compensation package.