UK Residency Programme - Novel Cloud Storage Technologies

Microsoft, Newtown, Cambridge

UK Residency Programme - Novel Cloud Storage Technologies

Salary not available. View on company website.

Microsoft, Newtown, Cambridge

  • Full time
  • Permanent
  • Onsite working

Posted 1 week ago, 13 Nov | Get your application in now before you're too late!

Closing date: Closing date not specified

job Ref: 549d65d0865b45f8a980407082226525

Full Job Description

In this role, you will work closely with other domain experts in computer systems, hardware design, physics, machine learning, and more to innovate and drive the design of next-generation cloud storage technologies. Possible areas of exploration include: analysis of Microsoft cloud workloads and systems; modelling and understanding of how various material and access characteristics would impact system-level performance; design and exploration of various system policies and configuration parameters through simulation; storage stack design; new resource management algorithms; error/erasure coding and disaster recovery; and more! Additionally, you will have an opportunity to participate in their research community by disseminating your work through publications, conference attendance and service, etc.

· PhD in computer science/engineering or equivalent industry experience in a research environment, with a focus on storage systems, distributed systems, operating systems, networking, or related.

· Capability for rapid and accurate development of research prototype code in C#, Rust, C/C++, Python, or similar.

· Creative and collaborative approach to problem solving.

· Strong communication skills and ability to communicate across technical boundaries.

Other Requirements:

Preferred/Additional Qualifications:

· Publishing track record in computer systems (e.g., SOSP, OSDI, NSDI, Sigcomm, Eurosys, FAST, ATC, SoCC, etc.)

· Experience successfully leading a computer systems research agenda.

· Experience working in large codebases.

Microsoft Corporation UK Residency Programme - Novel Cloud Storage Technologies in Cambridge, United Kingdom

The Cloud Infrastructure team at Microsoft Research Cambridge (UK) is seeking a highly motivated computer systems researcher to join us in inventing and prototyping the next generation of cloud storage systems. The demand for cloud storage continues to grow at a staggering rate, further fuelled by generative AI's insatiable appetite for data. We believe there's a massive opportunity for disrupting cloud storage (https://www.microsoft.com/en-us/research/uploads/prod/2020/07/hotstorage20_paper_chatzieleftheriou.pdf) , and we have built a world-class multidisciplinary research team spanning materials science, physics, engineering, machine learning, computer systems (and more!) to transform the area and invent the future of cloud storage. We've redefined the archival storage space with Project Silica (https://www.microsoft.com/en-us/research/project/project-silica/) , which is currently undergoing the transition from the research lab to product development. Silica highlighted the
tremendous opportunities and benefits that come from of co-designing every aspect of the system, allowing us to build sustainable, resource-proportional archival storage systems that adapt to the customer workload and offer unprecedented data durability guarantees at a fraction of today's costs.

We are now turning our eye beyond just archival storage to "hotter" data. Recent advances in machine learning / AI have fundamentally changed the scope of what is possible in many fields including materials discovery, scientific simulation, signal processing, and beyond. We are building on all these recent advances to rethink what storage devices for online cloud data should be in the era of power-constrained data centres, when the demand and need for low-cost, sustainable storage have never been greater. This includes pushing even further "down the stack" to also innovate at the layer of the media and how information is written to & read from it. This requires inventing new research methods that allow for rapid evaluation of how physics-level changes would translate into storage system-level impact on key metrics. Additionally, clean-slate system design also includes tackling the more "traditional" areas of

storage research (workload characterisation, scheduling, data placement, error/erasure coding, system policies, and much more) with complete design freedom.

This is an incredible opportunity to create the future of data storage, in collaboration with our fantastic team of multi-disciplinary researchers, and our partners in product teams across Microsoft.