Member of Technical Staff — Inference-Core Engine (AI)

Location: Palo Alto, California, United States

Annual salary: $200,000–$400,000 USD plus equity

Company

hirify.global is an infrastructure-first AI company building open systems for frontier-model inference and training.

What you will do

• Design and build large-scale inference systems for frontier AI models.
• Optimize latency, throughput, GPU utilization, and cost in production inference.
• Develop model-serving architectures, runtimes, batching, scheduling, and memory-management strategies.
• Collaborate with kernel, compiler, and systems teams on performance optimization.
• Debug bottlenecks across model, runtime, kernel, network, and system layers.
• Build observability, profiling, and performance-analysis tooling while driving infrastructure reliability and scalability.

Requirements

• 5+ years of experience in systems engineering, ML infrastructure, or performance-critical backend systems.
• Strong expertise in large-scale inference systems for LLMs or generative models.
• Deep understanding of GPU architecture, distributed systems, networking, and compute-intensive workload optimization.
• Experience optimizing latency- and throughput-critical production systems and debugging across system layers.
• Proficiency in Python, Rust, C++, or Go for production systems.

Nice to have

• Experience with SGLang, vLLM, TensorRT-LLM, CUDA, Triton, or custom kernel optimization.
• Open-source contributions in ML or systems infrastructure.
• Experience with batching, KV-cache management, scheduling strategies, inference at 1,000+ GPUs, HPC, or high-performance systems.

Culture & Benefits

• Infrastructure-first environment led by engineers with experience at xAI and NVIDIA.
• Work on open systems supporting frontier-level AI infrastructure.
• Equity included in the compensation package.
• Equal employment opportunity regardless of protected personal characteristics.