Hewlett Packard Labs – Research Engineer Simulation & Modeling

Key Skills

Java Programming, Design, Python Programming, C++, C Programming, SQL, FPGAs, Data Modeling, Infiniband, GPUs, Streaming APIs, Data Engineering, Large scale data processing, Data Architecture, Data Analysis

Job Description

Recent technology advances in heterogeneous compute, memory, and low-latency interconnects have enabled large-scale architectures at the confluence of HPC, AI, Data Analytics, and Enterprise domains. At Hewlett Packard Labs, our research team is inventing and developing the technologies for heterogeneous architectures to enable systems and applications of the future. The Hewlett Packard Labs research team is unique in the world, in that it focuses on all levels of the stack from core technologies to applications, and many layers in between. We offer the opportunity to do cutting edge research and see it become real.

We are seeking candidates with a PhD (or equivalent) in computer science or engineering, who are interested in a researcher and/or advanced development position. We expect candidates to have demonstrated the ability to frame, execute, and communicate research, for example, via papers published in top-tier conferences or journals, patents, as well as build substantial artifacts that validate their research. We value the ability to work alone and in teams, excellent verbal and written communication skills, strong computer science and engineering background, and the desire to learn new techniques to solve problems. Excellent software development skills for complex software systems are a significant plus.

About the Job

Primary areas of focus will be (in decreasing order of priority) in a) modeling and simulation of next generation hardware, software, and applications; b) hardware design and architectures; distributed systems and networking; c) system management, scheduling, and performance prediction; and d) software frameworks, programming models, and runtime systems for heterogeneous systems and AI;. Specific activities will include:

• Modeling and simulation systems, networks, systems software, and applications
• Performance evaluation, prediction, modeling, and simulation of future architectures
• Hardware architectures with embedded accelerators implemented as Smart NICs, and memory/compute side accelerators.
• Resource allocation and management, scheduling, fault resilience, coordination, and other system services in heterogeneous computing environment.
• Programming models that both hide and leverage heterogeneous system components, such as accelerators (GPUs, FPGAs, modern accelerators), memories (HBM, FAM, etc.), and interconnects (Slingshot, InfiniBand, etc.)

How You'll Make Your Mark

• Participates as a member of a research team focused on the design, implementation and assessment of application programming APIs and runtime systems software for future architectures to support the creation of new products, open-source software and intellectual property.
• Help in the creation of research plans, investigative procedures, and collection and analysis guidelines for the target investigation. Collaborate with internal and external partners to perform experiments and validations in accordance with the overall research plan.
• Participating in the design and implementation of system prototypes that are best suited for certain customer based requirements.
• Interacting with other teams who are developing adjacent hardware, firmware, software, mechanical, and thermal features that target these future data center systems.
• Communicate results and conclusions to team members for review and feedback.
• Prepare literature and presentations for peer review, publication, and delivery at industry and scientific events and conferences.
• Create patent applications and supporting documentation.
• Drive innovation and integration of new technologies and practices into research and product development organizations, as well as the open-source community.
• Provide guidance and mentoring to less experienced staff members.

About You

• PhD degree (or foreign equivalent) in Computer Science or Engineering.
• Proven capability to define and execute a research agenda.
• Proven capability to effectively work in a team-based environment.
• Familiarity with simulation tools, such as SST and gem5
• Familiarity with modeling techniques and performance evaluation
• A very high level of coding and debugging skills in both conventional languages such as C, C++ or Java, as well as scripting languages such as Python.
• Demonstrated ability to design, develop and debug large complex software systems.
• Strong background in performance analysis and tuning.
• Excellent written and verbal English communication skills.
• Familiarity with concurrency and software design for large scale multiprocessor NUMA systems is a plus.
• Familiarity and experience with complex memory models is a plus.
• Demonstrated ability to work constructively in an open-source community is a plus.
• Broad familiarity with processor and memory system hardware architecture is a plus.

What We Can Offer:

Extensive benefits, a competitive salary and participation in the shared values and purpose that make Hewlett Packard Enterprise one of the world´s most attractive employers! At HPE, our goal is to provide equal opportunities, flexible work-life balance, and constantly evolving career growth.