**Introduction** We’re seeking an enthusiastic computer engineer or software developer to help us ensure that the performance of AI-infused workloads running across on-premises and in our public cloud environments delights our customers. As part of the team that designs machines and software stacks that run many of the most demanding workloads used in Fortune-500 companies, you’ll play a key role in ensuring that our clients continue to love the performance of our systems both within their data centers and in IBM’s public cloud. You’ll focus on workloads that leverage artificial intelligence to solve real business problems, such as in the Retrieval Augmented Generation paradigm. You’ll help define and run workloads using cutting-edge technology and help identify and resolve performance challenges at all levels of the stack, from the hypervisor through the operating system right to the application layer. **Your role and responsibilities** In this role, you’ll be running workloads that simulate how clients apply artificial intelligence technologies to solve their problems. You’ll develop experimental plans to evaluate the performance of components like vector databases, vector encoders and of course various large language models, and how they run in diverse model serving frameworks and execution environments. You’ll study performance on CPUs as well as on off-chip accelerators. You’ll help us define targets for performance, and, when they’re not met, you’ll dive deeply into the stack and partner with developers and engineers from the hypervisor right through to model designers to identify and test solutions. Key Qualifications * Demonstrated understanding of modern artificial intelligence technologies such as large language models and vector encoders * Demonstrated understanding of micro-architecture design, memory layout, multi-threading, I/O buses * Experience with deploying, tuning and profiling applications running in Kubernetes environments * Experience deploying applications on at least one public cloud * Extensive experience with automation frameworks such as Ansible or Python * Knowledge of database design and some exposure to SQL is desirable * Ability to work in a team and network with people outside of the team and effectively communicate in written and verbal presentations is essential **Required technical and professional expertise** * Demonstrated knowledge of the architecture of modern artificial intelligence models, especially LLMs * Experience applying artificial intelligence technologies to solve problems * Demonstrated experience in micro-architecture design and implementation * 3 years of experience with a modern automation framework, Ansible preferred * Passion for continuous improvement in building knowledge base both technically and professionally * Minimum BS OR MS degree in Computer Engineering, electrical engineering, computer science or a related technical discipline or equivalent experience. **Preferred technical and professional experience** * Experience deploying hybrid cloud applications (that is, an application with an on-premises and a public cloud component) * Agile/ Scrum methodology experience