About the job
The Emerging Accelerators Team within HPE Labs has an immediate opening for a Principal AI/ML Engineer. HPE Labs is an international research organization with its headquarters and largest facility located in Milpitas, California. As the central research organization for Hewlett Packard Enterprise (HPE), HPE Labs' purpose is to deliver breakthrough technologies and technology advancements that provide a competitive advantage for the company, by investing in fundamental science and technology in areas of interest to HPE and getting the resulting technologies ready for adoption into new and existing markets.
Responsibilities
Synthesize research directions and vision based on technology insight and tracking advances across academia and industry. Define, lead, and delegate research activities while also contributing directly to research results. Research, conceive, develop, and model new architectures for AI/ML accelerator integrated circuits (IC) via simulators or system coding/analysis. Research, conceive, develop, and evaluate algorithms for AI/ML workloads on accelerator ICs or hardware, particularly in the Analog In-Memory Computing architecture space, potentially utilizing hardware/software co-design techniques. Research, conceive, develop, and evaluate compiler and mapping operations for optimal assignment of computational workloads to accelerator hardware. As a member of a project team in a leadership role, conceive, architect, design, and test integrated circuit IP for AI/ML research test chips. Conceive, architect, and design test and system boards and software for IC characterization and application demonstration. Provide technical guidance and mentorship for junior researchers, interns, and postdocs. Collaborate with internal and external technology partners. Author and provide guidance on conference presentations and journal papers reporting on new research results. Drive technical innovation leading to invention disclosures and patent filings.
Qualifications
Minimum
PhD degree in Electrical Engineering, Computer Science, Data Science, or equivalent. 5+ years of experience in AI & Machine learning ( academic or industrial). Must have strong experience in analog in-memory computing research, computing in memory, or processing in memory. Work experience with resistive RAM (ReRAM or RRAM) as a non-volatile memory device. Strong experience leading research projects. For candidates with only a Master degree, they must hold 10+ years experience in AI & ML research.
Preferred
Experience with in-memory computing accelerators. Experience with micro architecture design for custom accelerators. Experience in deep learning research, algorithms, and data structures. Experience in design and test of integrated circuit IP for AI/ML applications. Experience with emerging analog memory devices for computing applications such as RRAM, PCM, and others. Experience in system software, GPU acceleration, deep learning model execution and performance optimization. Experience working with FPGAs for emulation and system design. High level of creativity. Self-motivated and proactive, with strong leadership qualities. Ability to work with ambiguity. Ability to lead execution of complex projects. Demonstrated ability to generate, frame, and carry out leadership research as shown, for example, by papers published in top-tier conferences or journals.