Datacenter CPU Architect

CPU Architect Senior (L5 equivalent) 5-8 years

✓ Which company are you aiming at?

To generate precise rejection-prevention feedback and application strategy, tell us where you're targeting.

Apple

NVIDIA

Qualcomm

Intel

AMD

Arm

2 Send your application

You need an account so we know where to send the feedback.

Create an account Sign in

The job description

Tech stack. Server CPU architecture, gem5, PPA analysis, Python, datacenter workload characterization, TCO modeling, Arm and x86 server ISAs, virtualization architecture

About the role

You will architect server CPUs for datacenter deployment at a semiconductor company, designing processors where the scorecard is throughput per watt, throughput per dollar, and fleet-level reliability. Datacenter CPU architects optimize for the realities of warehouse-scale computing: highly parallel cloud-native workloads, virtualization overhead, strict power capping, and total cost of ownership measured across millions of deployed sockets. You will define core counts, cache hierarchies, IO capabilities, and efficiency features with the datacenter operator's economics always in view.

What you will achieve

Define the microarchitecture and configuration of server CPUs including core count, cache hierarchy, memory channels, and IO capabilities, optimized for cloud and enterprise workload performance per watt and per dollar.
Model datacenter workloads such as web serving, databases, analytics, and microservices at scale, ensuring the architecture serves fleet behavior rather than single-thread benchmark scores.
Architect virtualization and multi-tenancy features including performance isolation, quality of service, and security boundaries that cloud operators depend on.
Drive TCO analysis that connects architectural choices to operator economics, quantifying how performance, power, and reliability translate into datacenter cost per unit of work.
Define RAS (reliability, availability, serviceability) architecture appropriate for datacenter deployment, balancing error detection and correction costs against fleet failure rates.
Validate server CPU performance and efficiency on production-representative workloads, confirming the product meets its commitments in the environments where it will actually run.

What you will bring

Must-haves

5 to 8 years of experience in server CPU architecture, datacenter systems, or cloud infrastructure hardware with shipped products.
Strong understanding of server workload characteristics and how they differ from client or mobile workloads.
Knowledge of virtualization architectures, IOMMU, SR-IOV, and multi-tenant performance isolation techniques.
Experience with TCO thinking: connecting technical decisions to operator economics.
Performance modeling skills applied to throughput-oriented, highly parallel workloads.
Familiarity with server platform requirements including RAS, manageability, and firmware interfaces.
Data-driven decision making grounded in fleet-scale measurements rather than single-system benchmarks.

Nice-to-haves

Experience working directly with hyperscale or cloud customers on requirements.
Knowledge of emerging datacenter technologies such as CXL memory expansion or liquid cooling implications.
Background in networking or storage acceleration relevant to server SoCs.