Senior Staff Engineer - AI Workloads & Storage

Location: San Jose, California, United States

Base pay: $189,000–$301,000 USD annually

Company

hirify.global develops technology solutions spanning smartphones, electric vehicles, hyperscale data centers, IoT devices, NAND and SSD storage, and other computing systems.

What you will do

• Characterize production and emerging LLM inference, RAG, and training workloads, measuring I/O, bandwidth, latency, and capacity requirements.
• Translate workload access patterns into storage and memory-hierarchy architecture and optimize data placement using NVMe FDP and streams.
• Collaborate with customers on differentiating SSD capabilities and develop proof-of-concept data-path, tiering, and placement implementations.
• Analyze performance across inference runtimes, Linux storage and networking, and hardware, optimizing latency, throughput, cost, and GPU utilization.
• Build transactional, discrete-event, and system-level models to evaluate architectures before hardware implementation.
• Set technical direction, benchmarking practices, and architectural standards while mentoring engineers and partnering with product, hardware, research, vendors, and industry ecosystems.

Requirements

• 15+ years of relevant industry experience with a bachelor's degree, 13+ years with a master's degree, or 10+ years with a PhD.
• 10–15+ years of experience in systems, storage, or ML-systems software, including architecture work that improved performance, reliability, or cost.
• Working knowledge of modern AI inference and transformer serving, including attention, KV cache, batching, and memory/compute trade-offs.
• Deep understanding of Linux storage, NVMe, NAND/SSD internals, flash-translation layers, garbage collection, endurance, write amplification, and performance analysis tools.
• Fluency in Python and at least one systems language: C, C++, Rust, or Go.
• Technical leadership experience, including cross-team influence, architectural decision-making, and mentoring senior engineers.

Nice to have

• Experience with vLLM, SGLang, LMCache, NVIDIA Dynamo, TensorRT-LLM, or Triton.
• Knowledge of NIXL, DOCA MemOps, GPUDirect Storage, RDMA, NVMe-oF, BlueField/DPU offload, GPU/TPU architecture, or user-mode storage frameworks.
• SSD firmware, FDP, streams, ZNS, open-channel SSD, computational storage, PCIe Gen5, CXL, or large-scale GPU-cluster storage experience.
• Experience with AI benchmarking, SNIA Storage.AI, MLCommons/MLPerf, or modeling frameworks such as SystemC and SimPy.

Culture & Benefits

• Inclusive workplace focused on innovation, diversity, and employee empowerment.
• Medical, dental, vision, and 401(k) benefits.
• 4+ weeks of paid time off annually, plus holidays and sick leave.
• Family support benefits including fertility and adoption assistance, medical travel support, and virtual veterinary care.
• Emotional wellness resources, including confidential therapy sessions and wellness applications.
• Flexible work environment, with onsite café and gym access plus virtual fitness classes.