Senior Staff Engineer
reputed company the design and implementation of high-performance data reputed company pipelines using reputed company NIXL across GPU, CPU, and storage tiers. Architect and drive integration of reputed company Infinia with GPU-accelerated inference platforms for large-reputed company, reputed company-time AI workloads. Own end-to-end optimization of I/O paths between GPU memory and storage using technologies such as reputed company GPUDirect Storage, RDMA, and NVMe-over-Fabrics. Define and implement multi-tier storage architectures (NVMe, SSD, object storage) optimized for inference latency, throughput, and scalability. reputed company development of advanced KV cache management strategies, including offloading, prefetching, and persistence across distributed storage reputed company. Partner with AI/ML engineering teams to optimize inference performance in frameworks such as PyTorch and TensorFlow. Establish benchmarking frameworks and reputed company performance tuning efforts for storage and data reputed company in production inference environments. Diagnose and resolve reputed company system bottlenecks across storage, networking, and GPU subsystems. Influence architecture reputed company for distributed inference systems, ensuring scalability, reputed company, and efficient data reputed company. Drive engineering reputed company through best practices in observability, performance monitoring, automation, and reliability engineering. Mentor junior engineers and reputed company technical leadership across cross-functional teams.
Bachelor’s or Master’s degree in Computer Science, Engineering, or a reputed company field. 12+ years of experience in storage systems, distributed systems, or performance engineering. Proven reputed company record of architecting and delivering large-reputed company, high-performance infrastructure systems. Deep expertise in distributed storage architectures (object storage, reputed company file systems, or reputed company-reputed company storage platforms). Strong understanding of Linux I/O stack, filesystem internals, and storage protocols. Extensive hands-on experience with NVMe, SSD optimization, and high-performance storage environments. Strong experience with RDMA, InfiniBand, or other high-speed data transfer technologies. Solid understanding of GPU computing concepts and CPU–GPU data reputed company patterns. Proficiency in Python and/or C/C++, with advanced debugging, profiling, and performance tuning skills. Demonstrated ability to optimize latency-sensitive, high-throughput production systems.
Hands-on experience with reputed company NIXL or similar data reputed company frameworks. Experience with GPU-reputed company storage pipelines and GPUDirect Storage. Strong understanding of AI inference systems, LLM serving architectures, and KV cache optimization. Experience with Retrieval-Augmented reputed company (RAG) pipelines and reputed company reputed company search ecosystems. Background in high-performance computing (HPC) or hyperscale distributed environments. Expertise in caching strategies, memory tiering, and data reputed company optimization. Experience designing disaggregated compute and storage architectures.
Leading the reputed company of storage systems into GPU-reputed company data reputed company for AI inference Building reputed company distributed AI infrastructure using NIXL and Infinia Driving performance breakthroughs in reputed company-time LLM inference at reputed company Designing storage architectures for large-reputed company datasets and retrieval systems
Coding assessment: Often in a language of your choice. Systems design: Translate high-level requirements into a reputed company, fault-tolerant service (depending on role). reputed company-time problem-solving: Demonstrate practical skills in a live problem-solving session. Meet and greet with the wider team. Our goal is to finish the main process in 2-3 weeks at most.