Senior Software Engineer - LLM Infrastructure & HPC Clusters

Senior Software Engineer - LLM Infrastructure & HPC ClustersWithin this position you will be joining a Leading AI Innovation Team as a Senior Software & Infrastructure Engineer improving their generative AI products with automated testing and evaluation. We are working with a London-based start-up dedicated to engineering cutting-edge AI systems poised to revolutionize industries worldwide.As a leading Engineer, you will play a crucial role in developing a robust framework for rapid training and experimentation of large language models. Your responsibilities will include architecting an internal platform to facilitate high-throughput inference of these models. You will develop the core inference engine to seamlessly deploy large machine learning models to customers at scale and across distributed systems, contributing significantly to the automated pipeline, optimizing for high throughput training runs and rapid experimentation while achieving top hardware efficiency.Please note that this role requires in-person presence in London, but this role offers visa sponsorship and relocation support. Candidates should possess a minimum of 2-3 years of professional experience in a similar capacity.Qualifications:We are seeking candidates with exceptional engineering evidenced by:Experience in creating and managing high-performance computing clusters across GPU/TPU, preferably in PyTorch.Proficiency in efficient serving of large machine learning models at scale, including quantization and distributed computing, leveraging libraries such as deepspeed.Strong software engineering acumen with expertise in software design/architecture, particularly in Python.Understanding of the latest AI research and ability to efficiently implement these systems.Prior experience at a leading machine learning company (OpenAI, DeepMind, Meta, Anthropic, HuggingFace, etc.).Nice to Have:Experience as an early engineer at a fast-growing startup.Interest in and consideration of the impacts of AI technology.Key Words: Machine Learning / PyTorch / High Performance Computing / HPC / GPU / TPU / Deepspeed / AI / OpenAI / Distributed Systems / Big Data / ETL Pipeline / CUDABy applying to this role, you understand that we may collect your personal data and store and process it on our systems. For more information please see our Privacy Notice