5 months ago
Cambridge, United KingdomStaff+
Responsibilities
- Define, document, communicate, and maintain the architecture of the software stack from firmware to ML frameworks
- Ensure coherent end-to-end architecture across software domains and clarify components, interfaces, and guiding principles
- Assess the architectural impact of new technologies and account for usability, performance, reliability, maintainability, testability, security, and observability constraints
- Prototype and validate architectural concepts through proof-of-concept implementations
- Contribute to future product definitions and communicate the architectural impact of product direction
- Work with hardware and silicon architects to ensure product needs are met by the software stack
- Collaborate with engineering, product, leadership, and partners to align business goals with architectural direction
Requirements
- Expertise in one or more of firmware, drivers, ML frameworks such as PyTorch and Triton, collectives, HPC, tooling, C and C++, or CPU architectures
- Technical expertise in the ML accelerator software space
- Excellent written and verbal communication skills
- Collaborative mindset with the ability to influence
- Pragmatic, trade-off-aware decision-making approach
- Demonstrable experience in a previous architecture role is desirable
- Applicants must hold the right to work in the UK; visa sponsorship is unavailable
Benefits
- Flexible working and generous annual leave policy
- Private medical insurance, health cash plan, dental plan, pension matched up to 5%, life assurance, and income protection
- Generous parental leave and employee assistance programme
- Healthy food, snacks, and an on-site barista bar at the central Bristol office
- Applicants must hold the right to work in the UK; visa sponsorship is unavailable
- Reasonable interview adjustments are supported
About Graphcore
Graphcore designs and sells Intelligence Processing Units (IPUs), systems, and a full software stack for training and inference of AI models in data centers and research labs. Revenue comes from hardware systems and associated software tools and services, used for workloads across NLP, computer vision, and graph neural networks. Founded in 2016 and headquartered in Bristol, the company is part of SoftBank Group and focuses on on‑prem and cloud deployments.