Grid Computing

Hi,
Yahoo! Grid Services is searching 
for qualified Engineers to monitor and maintain our production grid (utility 
computing) clusters. 
Each cluster is thousands of nodes with petabytes of 
high-value data, 
running a distributed file system, map-reduce processing 
framework, 
and scheduling software. These resources are used to drive 
backend 
processing of various Yahoo! services. 

You will be working 
with various Yahoo! teams to deploy their processes 
on the grid and services 
are delivered as per the predetermined SLA . 

The primary computing platform is Hadoop, an Apache Software Foundation 
open source project for massively scalable utility computing. Yahoo! is 
a major contributor to Hadoop and related projects. You will have the 
opportunity to work with a significant open source project that will be 
adopted by some of the largest software and Internet companies in the world. 

The Grid team combines powerful open source packages, including Hadoop, 
a huge quantity of compute and storage resources, petabytes of data from 
a variety of sources, and support services to provide a utility computing 
service platform for the company. 

Responsibilities 

* Based 
on operational and project guidelines, work with independence 
and discretion 
regarding how to carry out tasks. 
* Take initiative to improve processes and 
help to plan for the 
future of the service. 
* Monitor cluster health and 
performance, use critical thinking to 
find areas for improvement. 
* 
Invent better ways to manage the existing clusters, via scripting 
and tools 
development. 
* Hardware and facility capacity planning, provisioning new 
resources. 
* Application profiling and performance analysis. 
* Real-time 
problem diagnosis/resolution on live systems. 
* Data load monitoring. 
* 
Systems monitoring and alerting. 
* Participate in a group pager rotation for 
emergencies for oncall 
support. 
* Devise schemes to transfer terabytes 
of data from diverse locations 
securely and reliably. 
* Reporting (html, 
e-mail, etc). 
* Resolve all operation issues, escalating engineering defects 
to the 
development organization. 
* Documentation on the running systems 
and their associated configurations. 

Minimum Job Qualifications 

* Experience as a Unix systems engineer in managing large installations 
* Strong shell scripting skills in at least one of awk, perl, or python. 
* Strong interpersonal and communication skills; capable of explaining 
simple procedures in writing or verbally; good phone skills. 

Preferred Job Qualifications 

* BS or MS in Computer Science (or 
equivalent). 
* Minimum 3 years experience as a Unix systems engineer 
* 
Knowledge and work experience with Java and Java profilers. 
* Cluster 
computing platforms like Condor, Torque, Maui / Moab , Sun Grid Engine. 
* Experience with programming models for large clusters: 
MPI, PVM, etc.  
 
All 
position will be based @ Yahoo! Bangalore . 
Kindly 
refer some of your friends to make your network 
active.


Please reply back with your updated profile if you are really interested in applying for this position.


Thanks In Advance