Platform Integration Engineer, Graviton Team
Posted 1
view
Annapurna Labs, as part of Amazon, is the team behind AWS (Amazon Web Services) Graviton — the industry's most advanced Arm-based server CPU — and we operate like a start-up with the scale of the world's largest cloud provider.
Our Graviton System group owns the design, manufacturing, and health of the Arm-based server fleet powering Amazon EC2 (Elastic Compute Cloud). We work close to the metal — across firmware, board bring-up, diagnostics, and hardware debug — to keep servers running and return failed units to production fast. In close partnership with design partners, data center operations, and hardware engineering teams, we bring new server platforms into the fleet and drive them to launch faster, healthier, and more reliably, at a scale that directly impacts millions of customers around the world.
If you are a systems, HW, or SW engineer who thrives on hard problems at the intersection of hardware and software, enjoys root-causing failures on real servers, and wants to see your work make a measurable difference across a global fleet — we would love to talk.
We're seeking for Platform Integration Engineer to own the development, testing, and monitoring of the manufacturing health of Amazon Graviton products integrated into MLA Trainium product. You will be part of a team integrating new silicon, hardware, firmware, and software into a revolutionary system architecture.
Key job responsibilities
- Lead product integration from definition phase through mass production, including: Hardware-Firmware integration and validation, development and implementation of manufacturing test flows, system validation and qualification and production readiness verification.
- Define and implement screening test content for both production line and data-center environments.
- Drive continuous improvement of operational health monitoring and debugging capabilities.
- Collaborate with cross-functional teams to resolve integration and production issues.
- Implement test flows for improving product operational health at manufacturing sites.
- Integrate knowledge and data from customers and data sources for fast resolution of operational issues.
- Maintain quality documentation and collateral in order to improve manufacturing operations.
- Travel to manufacturing sites as needed (approximately 3-4 times per year, 1 week duration per trip) to support integration, validation, and operational improvements.
Our Graviton System group owns the design, manufacturing, and health of the Arm-based server fleet powering Amazon EC2 (Elastic Compute Cloud). We work close to the metal — across firmware, board bring-up, diagnostics, and hardware debug — to keep servers running and return failed units to production fast. In close partnership with design partners, data center operations, and hardware engineering teams, we bring new server platforms into the fleet and drive them to launch faster, healthier, and more reliably, at a scale that directly impacts millions of customers around the world.
If you are a systems, HW, or SW engineer who thrives on hard problems at the intersection of hardware and software, enjoys root-causing failures on real servers, and wants to see your work make a measurable difference across a global fleet — we would love to talk.
We're seeking for Platform Integration Engineer to own the development, testing, and monitoring of the manufacturing health of Amazon Graviton products integrated into MLA Trainium product. You will be part of a team integrating new silicon, hardware, firmware, and software into a revolutionary system architecture.
Key job responsibilities
- Lead product integration from definition phase through mass production, including: Hardware-Firmware integration and validation, development and implementation of manufacturing test flows, system validation and qualification and production readiness verification.
- Define and implement screening test content for both production line and data-center environments.
- Drive continuous improvement of operational health monitoring and debugging capabilities.
- Collaborate with cross-functional teams to resolve integration and production issues.
- Implement test flows for improving product operational health at manufacturing sites.
- Integrate knowledge and data from customers and data sources for fast resolution of operational issues.
- Maintain quality documentation and collateral in order to improve manufacturing operations.
- Travel to manufacturing sites as needed (approximately 3-4 times per year, 1 week duration per trip) to support integration, validation, and operational improvements.