Google: Modeling Engineer - Mountain View

Modeling Engineer - Mountain View

This position is based in Mountain View, CA.

As a Modeling Engineer, you will champion Google?s breakthroughs in fraud detection and prevention across business models. You will apply your world class academic and professional experience towards the development of very innovative algorithms which will be engineered into Google products. You will use mathematical and statistical approaches, data mining and real-time data analysis, and traditional and unconventional algorithms to enable Google to launch new business models and scale operations while quickly driving fraud rates down to immaterial levels. You will be mathematically smarter than the fraudsters, and you will deliver quantum improvements to our products to keep Google several steps ahead of the bad guys. You will find ?Googly? solutions to the fraud problem.

An analogy of a Googly solution is how Google does language translations. The traditional approach called for hiring linguists, compiling translation rules, and designing a translation engine fueled by those rules. A small group of Google engineers took a very different approach and found a better way: Given that Google has access to millions of documents which are each translated into multiple languages, Google goes through those documents in an automated fashion, looks at translation patterns, records them, and applies the right combinations of those patterns to translating new phrases and documents. This approach has led to faster, lower-cost, and higher quality translations and a much more scalable model than the conventional approach. We need to think differently also in the fraud-risk prevention area.

In order to identify and stay ahead of fraudsters, you will leverage your PhD in mathematics, statistics, econometrics, operations research, or related field and your research. Professional experience in real-time data analysis in areas such as currency trading, futures, arbitration, etc. are further desirable qualifications for this position, although specific industry experience is not an absolute requirement. You will partner with Google engineers to translate your mathematical and statistical analyses of potential fraud situations into algorithms which are coded into internal and external Google products. You will be much more engineering focused than operations focused (i.e., you are looking for breakthrough solutions which we can build into our products as opposed to incremental solutions). Your solutions should not require material investments in risk/fraud administrators in our finance operations. Ideally you will keep a majority of fraud situations even from getting to our finance operations staff, which is what will enable us to scale our business.

Your approach to analyzing the data and defining actions from those analyses will be critical. You will define action from the smallest possible data set as close to real-time as possible. You will complement such real-time analysis with off-line data mining of broader data sets, but you will not solely rely on asynchronous data mining. And you and your engineering partners will, again, build those actions into products. You will actually strive to make our fraud-detection and prevention solutions to be self- optimizing.

Responsibilities:Development of fraud-detection and prevention algorithms and models into software products in partnership with engineering. Algorithms should be intelligent so as to learn and improve detection and prevention automatically.
Analyzing and understanding large amounts of Google?s historical business data and real-time customer (buyer and merchant)/transactional data for specific instances of fraud or broader fraud trends.
Data pre-processing for analysis, including clean-up and filtering.
Pattern identification, feature extraction, variable selection, and conversion of variables into fraud detection and prevention algorithms.
Experimenting with different types of algorithms and modeling techniques to control and prevent fraud.
Blend fraud-risk experience from within Google and outside with innovative mathematical/statistical approaches for data analysis and algorithm development.
Analyzing algorithm/model performance and driving fine-tuning of products as necessary.
Preparing metrics and model reports for communication with engineering and with business owners.
Requirements:PhD in Statistics, Mathematics, Econometrics, Operations Research, or related field.
Desired: Fraud detection and prevention analysis and solution design (engineering or operations).
Desired: Two years of experience in field requiring near-real-time pattern recognition, mathematical modeling, clustering/segmentation techniques, data analysis, and algorithm development for acting on analysis results (e.g. currency trading, futures, arbitration).
Familiarity with the latest modeling techniques and tools.
Excellent ability to communicate complex concepts orally, in writing, and via presentations.
Ability to learn new systems quickly.
Persistence to retrieve the data from all parts of the organization to perform daily tasks.
Responsive, problem-solving, multi-tasking self-starter.
Extreme attention to detail.
Very comfortable with UNIX, Linux.
Experience in both traditional and scripting languages: C/C++, Java, Python, Perl, etc.
Understanding of database architecture for data mining. SQL experience in querying large volumes of data a plus.
Working knowledge of SAS, SPSS, SLStat or other analysis tools.
Intermediate to advanced skills in Excel.


For immediate consideration, please apply HERE.


About Google:
Google's innovative search technologies connect millions of people around the world with information every day. Founded in 1998 by Stanford Ph.D. students Larry Page and Sergey Brin, Google today is a top web property in all major global markets. Google's targeted advertising program, which is the largest and fastest growing in the industry, provides businesses of all sizes with measurable results, while enhancing the overall web experience for users. Google is headquartered in Silicon Valley with offices throughout North America, Europe, and Asia. For more information, visit www.google.com.


Google is an Equal Employment Opportunity/Affirmative Action Employer.

To all recruitment agencies: Google does not accept agency resumes. Please do not forward resumes to our jobs alias, Google employees or any other company location. Google is not responsible for any fees related to unsolicited resumes.