Job Location : New York,NY, USA
Job Description We are looking for a senior contributor to design, develop and optimize AI frameworks for Inference. In this role, you will work with cross-geo teams to enhance the inference stack to ensure competitive performance on deep learning inference models with a specific focus on the PyTorch framework.The roles and responsibilities that you would need to perform may include the following:Design and develop SW techniques for AI frameworks - both HW-agnostic and HW-awareContribute to enhancing and extending the Inference and Training capabilities in our Software stackProfile deep learning inference workloads as needed and identify optimization opportunitiesQualifications BTech, MS or PhD in CS or related fields with an overall experience of 10 to 15 yearsAt least 2 or 3 years of experience working on Inference frameworks/tools for inference for deep learning models that have been deployed/used by customersArchitecture/Design contributions to Inference systemsDetailed understanding of machine learning systems optimization and deployment techniques such as quantizationExperience with optimization techniques for deployment of Large Language Models (LLMs)Deep implementation knowledge of transformers and inference specific optimizationsProgramming skills in Advanced C++, Python and parallel programming skillsAbility to debug complex issues in multi-layered SW systemsUnderstanding of SW integration across open source frameworks and internal framework layersStrong understanding of computer architectureEffective communication skills and experience with working in a cross-geo setupPreferredExperience working on and contributing to Inference serving solutionsKnowledge of compiler algorithms for heterogeneous systemsKnowledge of open source compiler infrastructure like LLVM or gccUnderstanding of low-level kernelsBenefits We offer a total compensation package that ranks among the best in the industry. It consists of competitive pay, stock, bonuses, as well as benefit programs which include health, retirement, and vacation.Working Model This role will be eligible for our hybrid work model which allows employees to split their time between working on-site at their assigned Intel site and off-site. In certain circumstances the work model may change to accommodate business needs.#J-18808-Ljbffr