System Hardware Engineer, Graviton server development team

Description

Annapurna Labs as part of Amazon, is looking for System Hardware Engineer to be part of defining, shaping and integrating solutions to next generation of our cloud platforms.

We are looking for exceptional engineer which will own developing, testing and monitoring the manufacturing health of Amazon Graviton server products, and will be part of a team which integrating new silicon, hardware, firmware and software into a revolutionary system architecture.

Key job responsibilities

• Define and provide feedback to design of Graviton servers and server components
• Work with design partners and manufacturer sites to enable the manufacturing of the Graviton based servers
• Review, identify and qualify second source electrical components to enable continuity of supply
• Continuously assess process capabilities and innovate to simplify processes, reduce cost, and shorten cycle time of Graviton server development and manufacturing
• Collaborates with cross functional team members to gain knowledge and improve product design, processes, and quality.
• Work with upstream vendors and downstream customers to optimize the entire value stream and put together joint processes that will lead better cost and cycle time.
• Willingness to travel 3–4 times per year (approximately 1 week per trip) to design partner and manufacturing sites.
  
  

• B.Sc. in Electrical Engineering (or equivalent).
• 6+ years of experience leading hardware products from design through mass production — including component selection, schematic/layout review, thermal/mechanical design, hardware-software interfaces, and production test development.
• 6+ years of hands-on experience in high-speed board design and signal integrity, with practical lab work on interfaces such as DDR4/5, PCIe Gen4/5/6, 100/400GbE.
• Demonstrated ability to conduct hardware bring-up, debug, and failure analysis in a lab environment — both on-site and at external design partner sites.
  
  

• Experience with CPU and peripherals architecture and design, particularly for multi-socket or accelerator-attached (GPU/AI) server platforms.
• Familiarity with PCIe Gen6, CXL, or high-speed SerDes interfaces and emerging interconnect standards for AI/ML workloads.
• Ability to analyze signal integrity / power integrity simulation results (e.g., from Ansys HFSS, Keysight ADS/PathWave, Cadence Sigrity) and recommend design tuning actions — such as stackup adjustments, termination strategies, decoupling optimization, and trace routing improvements. Practical experience with high-speed lab equipment (oscilloscopes, TDR, VNA, BER testers).
• Experience with sustaining engineering and production support — root cause analysis, ECO management, yield improvement, and vendor/CM collaboration.
• Working knowledge of scripting and automation (Bash, Python) for lab data analysis, test automation, or design flow scripting — including familiarity with AI-assisted automation tools for engineering workflows.
• Exposure to networking, storage, or Linux-based server environments.
• Technical leadership skills — ability to drive cross-functional execution across layout, SI/PI, firmware, and manufacturing teams in a matrix organization, including collaborative design work with ODMs and external design partners — managing technical alignment, design reviews, and milestone tracking across organizational boundaries.