Infrastructure + Alibaba + English Natives I know you loved infrastructure software and I know you are a guru at low-level stuff. But you didn’t seem to be able to find yourself doing too great of a thing anywhere. There are definitely exciting projects going on in some large companies of Silicon Valley. For examples, very large scale of cluster and resource management, contributing to docker software with lines of Go, docker-native kernel and OS, debugging some nasty Linux 4.4 bugs, writing a brand new storage system that is distributed with all new hardware gadgets like nvRAM, developing some RDMA or DPDK performance overhaul, working on a new garbage collector for Java, and so on. The only problem is, you don’t get to do it. There are always some seemingly “more experienced” programmers that are in charge of solving those really hardcore infrastructure problems, but you know you are actually better! If you have the above what I call the “chicken-hatching syndrome”, meaning you want to produce and you want to demonstrate yourself to be the best, yet you can’t find a good nest to hatch, ENTER ALIBABA. In case you did not know, Alibaba is a NYSE traded company with a market cap of about $260 billon. It is growing at 30-50% each year revenue-wise, because it does business of what Amazon, eBay and PayPal do (combined, so they are ANDs not ORs). Notably, its cloud service (Aliyun) is growing even more rapidly, injecting a new revenue stream into already-established e-commerce body of Alibaba. Your infrastructure instinct already tells you that Alibaba needs you. Yes, most definitely, because its infrastructure has to be the best, with no margin of inefficiency, simply due to its sheer size. Any imperfection costs us money, a lot of them. I look to you for the rescue. We do all crazy projects, including the mentioned ones at above, plus any other imaginable infrastructure pieces that you can help think of. You will be able to pilot them, because we’re starting many of those projects anew. I truly believe this is rare opportunity for someone like

you and you should definitely join me to do it together. Although I’m in charge of Infrastructure Software, I will be more like a programmer co-worker to you than a boss, because I’m also an infrastructure software engineer by heart, just like you. There may just be one remaining problem and you talk to yourself, that you don’t know how to speak Mandarin. I took care of this for you. You may work in Silicon Valley, as we have offices in San Mateo and Santa Clara, and you don’t have to speak Chinese. We have been working on internationalizing our workforce and it becomes ready to serve someone like you to make you feel native.

Still hesitating? Talk to me on Facebook or LinkedIn. Ready to send your resume? Send it to [email protected] Several proposed projects: 1. Docker-based Borg-like cluster and resource management system We’re looking for people who are very experienced with virtualization and container technology to build a new resource management system based on docker. Very large scale and very complicated scenarios guaranteed.

2. New generation storage system We will build a new distributed storage system that’s designed to be optimized with network and other hardware. This new system will help isolation of computation and storage yet without losing too much data locality, which is still much needed for machine learning and many other scenarios. 3. Docker-native kernel and OS Ready to build a new kernel or OS? We find this both challenging and necessary for our more and more docker-intensive environment. We look for true kernel and OS experts to explore in this direction that very few company cares about. 4. State of the art JVM Alibaba is a Java house. We use our own JDK. We will eventually open source ours. Will these three statements ring any bells to you? Come to join us to work on the hardest problem in Java, including resource containment inside JVM, co-routines, garbage collector, serializations, etc. Any one of these new features will be badly needed by many Java programmers in the world. 5. DNS, VR, Capacity planning and many others We actually have a broad spectrum of many other projects, including whole suite of software optimization toolsets, capacity planning software with machine learning, DDoS resilient DNS services for China nation, Virtual Reality (VR) Platform SDK that helps phone apps to quickly build VR applications, and still others. What’s even greater, if you find something interesting but not listed here, and you can convince us Alibaba should be doing it, give that a try! I have all ears for you here.

Infrastructure Software at Alibaba.pdf

New generation storage system. We will build a new distributed storage system that's designed to be optimized. with network and other hardware. This new system will help isolation of. computation and storage yet without losing too much data locality, which is still. much needed for machine learning and many other ...

196KB Sizes 2 Downloads 173 Views

Recommend Documents

How Software-Defined Infrastructure Is Evolving at Intel - Media15
For years, Intel IT has been evolving toward software-defined infrastructure (SDI), beginning with software-defined compute (SDC), to move from a proprietary fixed-function RISC Unix* compute ..... Enterprise applications that handle complex data war

How Software-Defined Infrastructure Is Evolving at Intel - Media15
In comparison, we started exploring open-standards-based software-defined technology in the storage environment in 2014. Additionally, enterprise support for open-standards-based technology is more robust for the server environment than for the netwo

Overlapping Experiment Infrastructure: More ... - Research at Google
Jul 28, 2010 - Android, Chrome, etc. At a high level, users interact with Google by sending requests for web pages via their browser. For search results pages, ...

ibex: An open infrastructure software platform to ... -
greatly expanded from primarily as a diagnostic tool to include a more central role in ... These differences mean that independent validation of pub- lished work is .... be easily added by defining them in library files in the developer studio ...

ArCMAPE: A Software Product Line Infrastructure to ... - IEEE Xplore
from Software Product Line Engineering to support fault-tolerant composite services ... ational software [1] by employing redundant software compo- nents called ...

Aging Distribution Infrastructure at Pacific Gas & Electric
difficult due to data limitations and a lack of analytical tools. The last difficulty with equipment inspection, maintenance, and replacement decisions relates to risk.

Research on Infrastructure Resilience in a Multi-Risk Context at ...
Earthquake performance of the built environment ... Increased land occupation ... Relation between each component damage state and a set of loss metrics (e.g..

Software Defined Networking at Scale - Research at Google
Google Confidential and Proprietary. Google's Global CDN. Page 7. Google Confidential and Proprietary. B4: Software Defined inter-Datacenter WAN. Page 8 ...

Building Software Systems at Google and ... - Research at Google
~1 network rewiring (rolling ~5% of machines down over 2-day span) ... services. • Typically 100s to 1000s of active jobs (some w/1 task, some w/1000s). • mix of ...

IRB Infrastructure - Nirmal Bang
May 4, 2012 - Earlier, the local police had conducted a detailed inquiry into ... Expressway), jointly owned by its real estate special purpose vehicle Aryan.

Green Infrastructure Plan -
Mar 13, 2012 - In exchange, DEC has eliminated approximately $1.4 billion in grey infrastructure projects, and agreed ..... 13 watersheds using updated impervious data based on a 2009 ...... sating and re-calculating changes in cloud cover,.