NYU School of Medicine is one of the nation's top-ranked medical schools. For 175 years, NYU School of Medicine has trained thousands of physicians and scientists who have helped to shape the course of medical history and enrich the lives of countless people. An integral part of NYU Langone Health, the School of Medicine at its core is committed to improving the human condition through medical education, scientific research, and direct patient care. For more information, go to med.nyu.edu, and interact with us on Facebook, Twitter and Instagram.
We have an exciting opportunity to join our team as a High Performance Computing (HPC) Architect.
This position will have an opportunity to contribute their talents to the growing and mission-critical effort within NYU Langone Health of bringing state-of-the-art HPC capabilities to the fingertips of our researchers and clinicians. In addition to the systems architectural activities this position will also help the HPC director lead a rapidly expanding group of motivated HPC technologists and computational scientists in providing a world-class research support and educational services.
Research, conceive, specify, select and evaluate complex compute, network and storage hardware solutions within a medical research and translational research environments in support of HPC strategic directions.
Analyze requirements for HPC research software stack to make sure that hardware and software layers interface properly.
Engage in software performance engineering activities to ensure that HPC environment is being used efficiently.
Provide hands-on systems integration support.
Work with Medical Center Information Technology (MCIT) Systems Architects and other technical staff, including datacenter managers, to make sure that HPC environment is compatible with the MCIT research computing environment.
Help formulate systems use policies, clearly communicate them to clients, and enforce them in a consistent manner.
Work toward integrating HPC environment into MCITs full data lifecycle management workflows.
Work with the MCIT Security and HPC staff to ensure that security and regulatory compliance is properly and consistently maintained across HPC systems.
Create runtime environment and design pathways for most efficient execution of jobs in HPC environment.
Design hardware solutions and create software platforms for collaboration activities both within and outside of NYU Langone Health.
Develop in-house software for systems usage monitoring, statistics gathering, and various accounting activities.
Lead development of performance metrics and instruments to gather information about research derivatives enabled by HPC.
Provide user training and develop reference materials for using applications.
Actively participate in various forms of customer support including ticket based troubleshooting and working with individual users on runtime and code debugging/profiling/optimization tasks.
Build relationships and assume leadership in contacts with information technology firms and computer equipment vendors.
Lead HPC systems administrators in their day-to-day activities.
Perform HPC systems administration tasks.
Perform other tasks as assigned.
3+ years of experience in HPC systems engineering field.
Demonstrated understanding of HPC architectural design and support pathways.
Advanced skills in Linux/UNIX systems programing and in distributed memory computer cluster systems administration on HPC platforms.
Thorough knowledge of a wide spectrum of HPC technologies.
Excellent verbal and written communication skills.
Masters degree in computer science or related field.
HPC Systems Architect experience.
Experience managing Linux/UNIX systems administrators or other HPC support staff.
Demonstrated expertise in integrating complex hardware and software solutions in HPC environment.
Proven ability to debug, profile, and optimize complex parallel scientific codes.
Proficiency in managing parallel file systems and Object Store solutions.
Expert knowledge of advanced networking technologies including switched fabric computer cluster interconnect technologies such as InfiniBand and OmniPath.
Understanding of HPC Vendors commercial space; established contacts with HPC Vendors.
Demonstrated knowledge of MPI programing and MPI implementation on distributed memory computer clusters.
Extensive knowledge of HPC resource managers and schedulers, in particular SGE and SLURM workflow managers.
Demonstrated expertise with GPGPUs and other accelerator technologies; proficiency in CUDA and OpenCL programming.
Knowledge of FPGA technology and its application.
In-depth knowledge of scientific software libraries.
Knowledge of virtualization; familiarity with OpenStack or other private/public cloud technologies.
Qualified candidates must be able to effectively communicate with all levels of the organization.
NYU School of Medicine provides its staff with far more than just a place to work. Rather, we are an institution you can be proud of, an institution where you'll feel good about devoting your time and your talents.
NYU School of Medicine is an equal opportunity and affirmative action employer committed to diversity and inclusion in all aspects of recruiting and employment. All qualified individuals are encouraged to apply and will receive consideration without regard to race, color, gender, gender identity or expression, sex, sexual orientation, transgender status, gender dysphoria, national origin, age, religion, disability, military and veteran status, marital or parental status, citizenship status, genetic information or any other factor which cannot lawfully be used as a basis for an employment decision.
NYU Langone Health, a world-class patient-centered integrated academic medical center, is one of the nation's premier centers for excellence in clinical care, biomedical research, and medical education. Located in the heart of Manhattan, NYU Langone is composed of four hospitals – Tisch Hospital, its flagship acute care facility; Rusk Rehabilitation; the Hospital for Joint Diseases, one of only five hospitals in the nation dedicated to orthopaedics and rheumatology; and Hassenfeld Children's Hospital, a comprehensive pediatric hospital supporting a full array of children's health services across the medical center – plus the NYU School of Medicine, which since 1841 has trained thousands of physicians and scientists who have helped to shape the course of medical history. The medical center's tri-fold mission to serve, teach, and discover is achieved 365 days a year through the seamless integration of a culture devoted to excellence in patient care, education and research. For more information, go to www.nyulangone.org.