Senior Hardware Engineer

Akamai•United States,

7h•$126,100 - $261,900•Remote

About The Position

Our Hardware Engineering team designs, qualifies, and scales the server platforms that power Akamai Cloud. We partner closely with OEM/ODM manufacturers to deliver reliable, efficient, and secure platforms from concept through global deployment. You'll focus on the SmartNIC/DPU software and hardware that underpins our compute and GPU servers. These DPUs offload CPU resources, improve isolation, and accelerate services across Akamai Cloud. You'll help define and integrate host + DPU architectures, validate RoCE and virtualization capabilities, and drive platform offload and acceleration from early concepts through mass production and global deployment.

Requirements

8 years of relevant experience and a Bachelor's degree in Computer Engineering or a related field
Experience with data center SmartNICs, or DPUs, including integration into x86/ARM servers and familiarity with PCIe, SR-IOV, and virtualization concepts.
Familiarity with DPU frameworks and languages such as NVIDIA DOCA/DPL, P4, DPDK, etc
An understanding of networking fundamentals, and familiarity with technologies such as congestion control and load balancing in data centers.
Experience with platform validation, PCIe/NVMe and networking qualification, and system-level stress testing
Linux skills and proficiency with scripting languages such as Python and Bash for automation and data analysis.
Comfortable working across HW/FW/SW boundaries, collaborating with teams to debug issues in the data path, control plane, and management stack.
Excellent written and verbal communication skills, including the ability to clearly communicate to both technical and non-technical audiences.

Responsibilities

Driving DPU hardware and software integration into Akamai compute and GPU server platforms, including PCIe, networking, storage, and manageability interfaces.
Planning and executing validation for DPU platforms, including functional, performance, interoperability, stress, and reliability testing for data-center scale use cases.
Implementing and validating networking and offload features such as RDMA/RoCE, L2/L3/L4 Ethernet/IP forwarding, SR-IOV/virtio-net/vDPA, overlay networks, and congestion control behaviors.
Developing automation, scripts, and test tooling to exercise DPUs, collect telemetry at scale, and turn results into requirements.
Collaborating closely with cross-functional teams to translate workload and SLO requirements into configurations and test plans.
Working with vendors to evaluate new DPU generations, firmware and feature updates, and trade-offs between performance, efficiency, supply continuity, and TCO.