Senior Software Engineer

At Graphcore, we’re building the future of AI compute. We’re a team of semiconductor, software and AI experts, with deep experience in creating the complete AI compute stack - from silicon and software to infrastructure at datacenter scale. As part of the SoftBank Group, backed by significant long-term investment, we are delivering key technology into the fast-growing SoftBank AI ecosystem. Graphcore is expanding its teams around the world to solve tough problems and impact the future of artificial intelligence.

Essential:

• A passion for your work and the ability to thrive in uncertain and complex environments
• Strong programming skills in Python, C, and C++ with a focus on performance-sensitive applications
• Solid understanding of computer architecture, performance profiling, and low-level system behaviour (CPU, memory, I/O)
• Experience with benchmarking and analysing complex, distributed systems
• Familiarity with Linux-based development environments and tools
• Strong problem-solving skills and ability to interpret and communicate performance data clearly

Desirable:

• Knowledge of ML frameworks (ideally PyTorch) and their performance characteristics
• Experience with performance analysis in GPU-accelerated environments (CUDA, ROCm, etc.)
• Familiarity with hardware performance characteristics especially in ML context including high-speed networking (e.g. RoCE, RDMA)
• Familiarity with distributed computing frameworks (ideally collectives experience)
• Experience building dashboards or visualizations for performance monitoring (e.g., Grafana, Prometheus, or custom tooling)
• Exposure to performance regression tracking and CI pipelines for performance validation

• Own performance analysis across the full ML stack, from model execution down to hardware utilization
• Identify bottlenecks and regression trends using profiling, benchmarking, and deep system analysis
• Drive cross-team optimizations involving frameworks, compilers, runtime, and infrastructure
• Design and maintain benchmarking environments for synthetic, focused benchmarks up to large-scale ML workloads
• Produce performance reports that translate low-level findings into actionable insights
• Ensure local optimizations improve global system performance, not just isolated components
• Partner with engineering teams to guide performance improvements and validate impact