AI Performance Engineer

Charterhouse are partnered with a fast-growing technology company in the region, who are pioneering the development of advanced server hardware tailored for artificial intelligence (AI) and machine learning (ML) workloads. Our Client is dedicated to accelerating AI innovation by delivering high-performance, scalable, and energy-efficient infrastructure solutions. As part of their expansion, they are looking to hire experienced AI Performance Engineers (multiple openings) to join their team.The AI Performance Engineer will be responsible for profiling and enhancing the performance of AI workloads across various hardware platforms and machine learning frameworks. The position involves experimenting with model optimization techniques such as quantization, pruning, and compression, while also diagnosing and resolving performance bottlenecks in complex computing systems. The engineer will collaborate closely with software and firmware teams to ensure that end-to-end application performance goals are met, without compromising development efficiency.The ideal candidate will have at least five years of experience in Python and C++ programming, along with a deep understanding of the internals of ML frameworks like PyTorch and TensorFlow. Practical experience in training and deploying models, working with distributed systems, and managing parallel workloads is essential. The successful candidate will have a deep understanding of CPU, GPU, or custom accelerator architectures such as NPUs or TPUs, as well as low-level optimization techniques. Experience with LLM development or deployment would be highly beneficial.The role is open to candidates globally, those with a passion for performance engineering and a strong technical foundation are encouraged to apply. This is a unique opportunity to contribute to cutting-edge AI infrastructure projects in a fast-paced and innovation-driven environment.