Senior Staff Engineer (AI Data Path & Storage)

Location: Remote in California with a hybrid work arrangement

Company

hirify.global develops the Infinia Data Intelligence Platform and advanced storage infrastructure for AI inference and large-scale distributed workloads.

What you will do

• Lead the design and implementation of high-performance data movement pipelines using NVIDIA NIXL across GPU, CPU, and storage tiers.
• Integrate hirify.global Infinia with GPU-accelerated inference platforms for large-scale, real-time AI workloads.
• Optimize GPU-to-storage I/O paths using GPUDirect Storage, RDMA, InfiniBand, and NVMe-over-Fabrics.
• Design multi-tier storage architectures and advanced KV cache strategies for latency, throughput, scalability, and data locality.
• Partner with AI/ML teams to optimize PyTorch and TensorFlow inference performance and establish production benchmarking frameworks.
• Mentor engineers and provide technical leadership across architecture, observability, automation, reliability, and performance initiatives.

Requirements

• Bachelor’s or Master’s degree in Computer Science, Engineering, or a related field.
• 12+ years of experience in storage systems, distributed systems, or performance engineering.
• Deep expertise in distributed storage architectures, Linux I/O, filesystem internals, storage protocols, NVMe, SSD optimization, and high-performance environments.
• Hands-on experience with RDMA, InfiniBand, GPU computing, CPU–GPU data movement, and latency-sensitive production systems.
• Proficiency in Python and/or C/C++, including advanced debugging, profiling, and performance tuning.
• Must be based in California and work in a hybrid arrangement.

Nice to have

• Experience with NVIDIA NIXL or comparable data movement frameworks and GPUDirect Storage.
• Experience with AI inference systems, LLM serving, KV cache optimization, RAG pipelines, and vector search ecosystems.
• Background in HPC or hyperscale distributed environments.
• Experience with caching, memory tiering, data locality, and disaggregated compute and storage architectures.

Culture & Benefits

• Hands-on work on GPU-native storage layers for AI inference.
• Opportunity to build next-generation distributed AI infrastructure using NIXL and Infinia.
• Focus on performance breakthroughs in real-time LLM inference at scale.
• Technical leadership and cross-functional collaboration across storage, networking, GPU, and AI/ML engineering.