System Engineer, remote
About the job
Xinnor is an Israeli-based software development company that specializes in creating innovative data storage solutions. Our main product xiRAID is a patented software RAID technology that delivers exceptional performance.
xiRAID works with all storage devices and excels when deployed alongside NVMe® or NVMe-oF™ devices. It is the only solution on the market to drive up to 95% of raw device performance in a computationally heavy RAID6/RAID N+M configurations with a low load on the host CPU and memory footprint.
Basing on our xiRAID technology we do with our partners:
- Software design in cooperation with HW and SW vendors (Western Digital, Intel, Kioxia, Samsung just to mention a few) and their specialized research labs.
- Software defined storage for high performance computing clusters for scientific and industrial applications.
- Solutions for different industries: Media&Entertainment, Telecom, Finance, Automotive.
We are all about performance and looking for software engineers who want to be a part of the young and very ambitious team blended with our more than 10 years research experience and existing product selling worldwide.
- Research and measure storage performance for High Performance Computing (HPC) workloads.
- Maximize performance at the integration layer with parallel or distributed file systems.
- Document and update best practices, procedures, and policies for HPC and SDS clusters. Knowledge sharing with other engineers.
- Provide timely and professional support to HPC cluster admins and customers.
- Work with other HPC engineers to design and implement scalable and efficient solutions for big data applications.
- Present results to the customers or at public events and conferences.
- Participate in pre-sales.
The following skills will help you be successful on the job:
- In-depth knowledge and hands-on experience with the hardware architecture of modern drive subsystems and servers.
- Understanding and ability to identify components responsible for application performance degradation, bottle-neck localisation to the specific component (kernel/application lines of code, hardware component), finding root causes of computational failures.
- Experience in using of tracing and profiling tools (Dtrace, SystemTap, perf, strace, eBPF).
- Deep knowledge in Linux system administration, knowledge of any modern scripting language: e.g. Python or advanced knowledge of BASH.
- Deep knowledge in one or more parallel or distributed filesystems such as Lustre, GPFS, BeeGFS, etc.
- Understanding of methodologies and principles of load testing, automated testing.
We Offer You:
- Challengeable tasks: you will feel yourself as an inventor solving tasks not solved before.
- Everything about performance: CPUs and DPUs, drives, buses, communication protocols.
- Work together with the best industry talents with ability to learn.
- Fast growing company & International environment.
- Flat organization with possibility to make an impact.