Reference # 18-01607 Title HPC Developer
Location New York City, NEW YORK
Position Type Contract
Experience Level Contract
Start Date / End Date 12-09-2018 --- 30-11--0001
Job Title: HPC Specialist
The grid engineering team at Brokerage is responsible for managing the infrastructure of thousands of servers which are used to run risk calculations.

The role includes overseeing the Brokerage HPC grid spanning multiple data centers and occupying over 10,000 servers and 250K cores
The group is also involved in deploying grid applications to IBM Soft layer and AWS.
Required expertise include HPC computing, Linux, networking, automation and Public Cloud apart from excellent inter-personal skills.
The work will involve optimizing the infrastructure from an operating system and networking perspective.
It will involve working closely with the application developers and support teams.
The candidate will be involved with engineering infrastructure to migrate to the Public Cloud.
The candidate needs to have experience with HPC technologies, sound infrastructure knowledge and good development
Skills Required:
Redhat Enterprise Linux engineer level knowledge Strong scripting skills in Python Experience with HPC Linux/Unix System Administration
Preferred: Infrastructure deployment experience in the Public cloud Knowledge of security controls for the Public cloud ( encryption of data in motion/rest and key management )
Experience with distributed, parallel file systems and related tools (GPFS, CFS etc.)
Monitoring/Visualizing products like Zabbix, Splunk, Extrahop, Sevone or similar, the RRD file format Central config management system for Linux experience (Puppet, Chef, etc.)
Knowledge of Linux containers Experience in the financial industry GPU's and FPGA's Agile Engineering is a group within Enterprise Computing ( EC ) responsible for architecting a container based platform for Brokerage.
This platform is widely used by a large number of internal applications.
We are also looking to extend this platform to the Public cloud.
This platform will also need to be ported to an internal secure network whose characteristics are similar to the Public Cloud The work will involve engineering a cloud agnostic, redundant, highly scalable infrastructure platform to on-board the internal MS applications and deploy to Public Cloud vendors like AWS, Azure and Softlayer