Skip to content
Limestone AI Labs
Menu

Data-center design

Sizing, power, racks, and network, planned before anything ships. A room, a cage, or a colocation pod, designed on paper first so the hardware arrives to a plan.

Scope this project All nine services
Scope

What the work covers.

  • Capacity sizing

    Compute, storage, and growth sized from what you run today.

  • Power & cooling

    Power budgets and cooling needs worked out rack by rack.

  • Rack elevations

    Every device placed, labelled, and cabled on paper first.

  • Network plan

    Switching, uplinks, and the management network designed with the racks.

  • Colocation

    Requirements written for the colo; their remote hands or a local installer does the racking.

Every project runs Discovery, Design, Build, Handover. How we work

Platforms

What we build on.

  • Dell PowerEdge
  • Lenovo
  • Nutanix
  • Cisco Nexus
  • FortiGate

Hardware and licensing through MQ3 Labs, or bring your own.

Track record

Where we have done it.

  1. AI infrastructure
    Network design for a GPU data center.

    SONiC switch plans for a 100-server pod, hardware through MQ3 Labs.

  2. Enterprise
    A 5,000-person insurance company, built and run end to end.

    Its data center, a Nutanix and Rubrik core, Meraki across 120-plus sites, and company-wide Citrix.

Client names stay private. All selected work

Before you write

A useful first email covers four things.

  1. 01 What runs today: servers, storage, and the workloads on them.
  2. 02 Where it is going: a server room, a colo cage, or a new pod.
  3. 03 The power and space you have, if you know it.
  4. 04 The date the hardware needs to be live.

Missing some of it? Send what you have; we will work out the rest together.

Questions

Scope questions.

Do you rack the hardware?
We plan the room, racks, power, and network, then configure the systems remotely. Your team or the colo's remote hands usually rack and cable; we can coordinate a local installer.
Can you plan for GPU servers?
Yes. We have designed the network for a 100-server GPU pod. Tell us the servers and the workload.

Pricing, hardware, and other common questions

Get in touch

Start with a conversation.

Tell us about your project and timeline. Expect a written reply within one business day, from the engineer who will do the work.

Prefer email?
hello@limestoneailabs.com
Existing clients
Sign in to the client portal →