Software Engineer - Triton

Build the framework support that helps AI developers unlock Graphcore hardware. You will help Graphcore accelerators work seamlessly with state‑of‑the‑art ML frameworks, including Triton and PyTorch. Reporting to a Team Lead in Frameworks, you will design, implement, optimise and support critical software. Your work will shape how researchers and engineers use Graphcore hardware for demanding machine learning workloads. You will improve performance, quality and usability across a complex software stack. You will join our Triton team, delivering new features, reviewing code, writing technical documentation and working with upstream communities. You will also help coordinate open‑ended technical work across teams. This role offers deep technical ownership and visible impact as the ML software landscape evolves. You will keep learning and may contribute across other framework teams.

The Frameworks team connects Graphcore hardware with the tools ML engineers and researchers rely on. We work across PyTorch, Triton, JAX and TensorFlow, focusing on usability and performance. Work happens through agile practices, close technical discussion and clear ownership. Engineers are trusted to speak up, solve hard problems and move work forward with pace. Decisions are shaped by evidence, code quality and business outcomes. You will work across Graphcore and with open‑source communities to deliver software developers can trust.

What we’re looking for:

• Strong software engineering skills, with the judgement to manage quality, complexity and technical debt.
• Experience developing in Python and C++.
• Experience in compiler development.
• Ability to manage complex technical tasks with cross‑team dependencies.
• Clear communication skills, with a proactive approach to collaboration and technical leadership.
• Interest in AI, ML frameworks, performance optimisation or computationally intensive engineering.

Benefits:

• Flexible working: Balance your work and personal life with greater flexibility.
• Generous leave: Take time to rest, recharge and enjoy life outside of work.
• Retirement planning support: Up to 5% matched pension.
• Phantom equity: Share in Graphcore’s success.
• Workplace experience: Enjoy thoughtfully designed office spaces for collaboration, with free food and an on‑site barista to support your day.
• Peace of mind protection: Income protection and life assurance to provide financial security for you and your loved ones.
• Flexible benefits: Tailor your benefits package with a choice of additional options, including private medical insurance and dental cover.
• Optional benefits: Dental cover, health cash plan, private medical insurance, cycle to work scheme, give as you earn.

We welcome people from all backgrounds and experiences and are committed to building an inclusive environment where everyone can do their best work. We’re an equal opportunity employer and recognise that everyone brings different strengths and perspectives. If you need any adjustments during the interview process, just let us know - we’re happy to support you.

Graphcore is one of the world’s leading innovators in Artificial Intelligence compute. It is developing hardware, software and systems infrastructure that will unlock the next generation of AI breakthroughs and power the widespread adoption of AI solutions across every industry. As part of the SoftBank Group, Graphcore is a member of an elite family of companies responsible for some of the world’s most transformative technologies. Together, they share a bold vision: to enable Artificial Super Intelligence and ensure its benefits are accessible to everyone. Graphcore’s teams are drawn from diverse backgrounds and bring a broad range of skills and perspectives. A melting pot of AI research specialists, silicon designers, software engineers and systems architects, Graphcore brings together deep expertise to solve complex problems and deliver meaningful progress in AI compute. We’d love to hear from you if you want to shape the frameworks developers use to push AI compute forward.