HPC Architect - US Group in Hyd

Job Description

HPC ArchitectThe HPC Cloud Architect will administer high performance scientific computing platforms, infrastructure, and support research projects.

• Utilize your experience in multiple disciplines including high performance computing (HPC), cloud, architecture, design, network, security and systems to implement and provide advanced system engineering services to customer.
• Manage, administer and support daily operation of computing systems both onsite and in the cloud.
• Design, implement and maintain scalable High-Availability (HA) and Fault-Tolerant (FT) computing systems.
• Following the best cloud computing practice by utilizing Amazon Virtual Private Cloud (VPC), Amazon Elastic Computing Cloud (EC2) and other advanced technical cloud features.
• Investigate and provide technical options to managers and researchers for selecting effective computing solutions based on requirements.

Experience:

• 8-10 years of hands-on systems administration/engineering experience with Linux.
• Experience with high performance computing systems in Life Sciences will be added advantage, Engineering, Manufacturing or Financial Services
• Minimum three years with Amazon Web Services (AWS) cloud computing.
• Extensive administration experience in GPU-based platforms.
• Excellent written and oral communication skills and ability to work with people at every level.

Required Skills:

• Demonstrated experience in optimizing computing performance and measurement.
• Comprehensive knowledge of security compliance and security control.
• Proficient skills in shell scripting, Ruby, Perl or Python.
• Excellent organization and time management skills and ability to identify priorities to accomplish a variety of tasks simultaneously.
• Comprehensive knowledge in Configuration Management (CM) process and software development tools such as Git, GitLab, Nexus, Jenkins, Maven or JIRA.
• Working knowledge of HPC schedulers and distributed/parallel file systems, underlying IT systems, and the HPC development process, high throughput and tight coupling approaches
• Knowledge of statistics, numeric modeling, data analyzing and machine learning.
• AWS certification at Professional level.
• Experience with cloud CLI and SDK.
• An understanding of the cloud computing delivery model as it relates to HPC
• Knowledge of the underlying infrastructure requirements such as Networking, Storage, and Hardware Optimization.
• Experience in a customer-facing, sales-aligned role such as consultant, solutions engineer or solutions architect
• Track record of implementing AWS services in a variety of business environments such as large enterprises and start-ups.
• AWS Certification, eg. AWS Solutions Architect Associate
• Understanding of application, server, and network security
• Experience in DevOps tools like Ansible Tower,Bitbucket, Terraform, and CloudFormationetc.
• Experience in Linux Administration various distributions like Redhat, Amazon, CentOS
• Experience with job schedulers like Grid Engine, LSF, PBS, SLURM, Torque, Symphony, TIBCO.
• Experience with compilers and libraries such as MPI, GCC, CUDA etc.
• Experience with scripting (bash, Python, PowerShell, etc.).
• Experience in Filesystems like NFS, Lustre/GPFS, etc.,
• Experience in Application installations and troubleshooting on HPC Clusters based on CPU, GPU.

Certifications (Desirable)

• AWS Administrator Professional or up
• Linux Administration

Responsibilities

• Responsible to architect a framework that is more readily available and demonstrate ease of use. When factoring new architecture make build v/s buy decision and consider cost aspects.
• Work in coordination with other internal teams to ensure the infrastructure fully and effectively supports current and planned application systems.
• Troubleshoot OS, Networking, Storage, and Software issues while leveraging internal teams for solutions.
• Deliver changes to the HPC production platforms according to the change control process. Communicating and seeking approvals from business owners.
• Practice network asset management, including maintenance of network component inventory and related documentation
• Develop tools to deploy, manage, monitor, and troubleshoot HPC systems at scale.
• Maintain asset lists of all servers, applications and licensing ensuring compliancy.
• Maintain security standards according to internal policies.
• Execute the day-to-day activities of the Incident Management process
• Manage and respond to tickets/requests in accordance with SLA timeframes.
• Develop tools to deploy, manage, monitor, and troubleshoot HPC systems at scale.

Optional Skills

• Docker, Singularity, Kubernetes, GCP will be a plus.
• Knowledge of distributed computing
• Ansible, Jira, Confluence, Service Now, Excel, Presentation Skills
• Worked on building clusters with individual machines (not a service like EMR etc

Keyskills :
asset managementtime managementprivate clouddevelopment toolsweb servicesfile systemshigh performance computingshell scriptingfinancial servicescloud computingnetwork securityamazon web servicessoftware development toolscommercial modelscont