Staff Engineer (ML Engineer)

Graphcore seeks a Staff ML Engineer to validate and benchmark its AI compute stack, ensuring ML models run reliably on accelerator hardware. The role involves building automated benchmarking pipelines, testing low-level ML behaviors like numerical precision and quantisation, and collaborating closely with software, hardware, and infrastructure teams to expose regressions and performance limits before customer release.

• Validate and benchmark ML models and frameworks on Graphcore's hardware/software stack.
• Build automated benchmarking pipelines and run open-source model tests.
• Create targeted tests for numerical precision, quantisation, attention mechanisms, distributed execution, and model subgraphs.
• Expose regressions, correctness issues, and performance limits before customer release.
• Collaborate with software, infrastructure, and hardware teams to improve ML stack quality.

• Strong experience in Machine Learning or ML-adjacent software engineering.
• Solid grasp of neural networks, training, inference, numerical precision, and performance trade-offs.
• Hands-on experience with PyTorch, TensorFlow, JAX, Triton or similar ML frameworks.
• Strong Python skills for automation, experimentation, benchmarking, and reporting.
• Experience designing, running, and analyzing ML benchmarks or model experiments.