Top Engineering Jobs

The Director of Software Architecture leads the software architecture vision for Graphcore’s ML accelerator, managing a team and engaging with stakeholders to ensure alignment with business goals. Responsibilities include defining architecture processes, advocating user experience, and mentoring the architecture team.

The SoC Architect designs, specifies, models, and integrates subsystems for high-performance silicon devices, collaborating with other teams and influencing design trade-offs, while guiding engineers and mentoring technical staff.

The Principal SoC Architect will design, specify, and integrate subsystems in AI acceleration technology, collaborating closely with various engineering teams and managing technical objectives.

Develop production-grade Go services for Kubernetes integration of AI accelerator hardware, ensuring performance, reliability, and scalability of infrastructure.

As a Silicon Logical Design Engineer, you will produce high-quality microarchitecture and RTL, collaborate across teams, and help ensure successful chip delivery.

This role involves advanced troubleshooting, validation, and operational support for AI compute hardware, collaborating with engineering teams to ensure system performance.

The Principal Test Framework Software Engineer will design and implement test automation frameworks for hardware validation, collaborating with teams to ensure quality and efficiency in AI hardware systems.

As a Senior Software Engineer, you will develop and support kernels for linear algebra operations on AI hardware, ensure performance and correctness, and mentor team members.

The Principal Reliability Scientist leads reliability activities in high-performance systems, drives experimental design, analyses data for reliability metrics, and collaborates with cross-functional teams to enhance product reliability and serviceability.

Design, develop, and implement diagnostics software and tools for hardware monitoring and fault diagnosis in AI systems. Collaborate with multiple teams to ensure system reliability.