Graduate Software Engineer, Frameworks 2027

Job description

Location: Bristol, UK Start date: September 2027 Application deadline : Midnight, 29th November 2026 We encourage you to apply early, as we may close applications before the advertised deadline. The Graduate Programme at Graphcore Join Graphcore in a permanent role and start your career with two years of hands-on learning. From day one, you’ll be trusted to take ownership, share your ideas and help shape what we’re creating. You’ll tackle challenging problems alongside a team who support your development and are as excited about your success as you are. What you’ll work on Help build the software that connects Graphcore hardware with the machine learning frameworks researchers and engineers rely on. As a Graduate Software Engineer across our Frameworks team, you’ll develop software connecting Graphcore’s machine learning accelerators with frameworks including PyTorch and Triton. You’ll implement features, optimise performance, resolve defects and create tests and technical documentation. You’ll write and improve tests, investigate issues and help make the software more reliable and faster. You’ll also write clear documentation and take part in code reviews, discussing ideas and learning from feedback. Take ownership of clearly scoped tasks, with support from experienced colleagues as you learn your way around the codebase. Your team and support The Frameworks team works with tools including PyTorch and Triton Its work connects these tools with compilers, which translate code for hardware, and runtime software, which helps it execute. We plan and review work in short cycles using Scrum. You’ll have clear priorities, regular feedback and opportunities to learn from colleagues working across software and hardware. Technical evidence and the needs of our users help guide our decisions. You’ll be encouraged to ask questions, challenge existing approaches and share ideas for making things better. Take responsibility for your work and speak up when you spot a problem or need support. How you’ll learn and grow During the two-year programme, you’ll build your understanding of how software and hardware work together to run AI workloads. Hands-on tasks will help you develop your knowledge of compilers and runtime software, alongside your skills in testing, debugging and documentation. Code reviews and technical discussions will give you feedback on your approach and h…