BlackRock helps investors build better financial futures.As a fiduciary to our clients, we provide the investment and technology solutions they need when planning for their most important goals. As of December 31, 2017, the firm managed approximately $6.288 trillion in assets on behalf of investors worldwide.For additional information on BlackRock, please visit www.blackrock.com | Twitter: @blackrock | Blog: www.blackrockblog.com | LinkedIn: www.linkedin.com/company/blackrock.

Job Description:

Business Unit Overview:

BlackRock Data Services (BDS) is BlackRock’s main data processing and quality control group – 700+ people globally ensuring our data is delivered, completely and accurately, to our clients, users and downstream systems in the appropriate formats.

This includes data on clients, portfolios, index portfolios, positions, security terms and conditions and pricing, portfolio net asset values and cash, risk and returns calculations, compliance with investment guidelines and more. Our production and quality control platform currently analyzes tens-to-hundreds of millions of data points daily – and more than that on a weekly/monthly frequency. BDS’s Data Engineering group continually advances this platform, through projects large and small.

Our team (Data Science and Operations Analytics) works with BDS and other departments to develop more innovative ways of working. Some solutions address specific business problems; some tools solve a whole class of problems; and we also consult units as needed. Core knowledge includes applied math and statistics, data science and machine learning, software development, business process re-engineering, and knowledge of finance and the investment process.

The interdisciplinary nature of our work and the breadth of business functions we partner with give our staff an excellent introduction to much of the BlackRock organization as well as flexibility in longer-term career growth opportunities.

Job Description and Responsibilities:

• Using NLP and ML techniques and our robust structured databases to:

1. Extract investment information from documents such as term sheets, prospectuses, contracts, fact sheets and more.

2. Analyze documents and electronic communications (such as email) for content;

Automate classification and prioritization of email-generated requests;

Where feasible, facilitate/suggest resolution to a request;

Double-check that request fulfilment was done properly, according to the details of the request.

3. Catalogue properties of and relationships between different types of data;

Automatically recognize and categorize different types of data;

Facilitate conversion of data between our business partners’ systems and our own;

Responsibilities include:

• Help define our long-term NLP and ML strategy; lead and contribute to projects that execute on it.

• (Potentially) Manage people to execute against said strategy.

• Use statistical NLP to mine unstructured data for business insights;

• Build methods for document clustering, topic modelling, text classification, named entity recognition, sentiment analysis, and part-of-speech tagging

• Analyze and model structured data using advanced statistical methods and build algorithms and software needed to perform analyses

• Develop solutions and tools to support diverse business needs; communicate results and educate others through presentations and demonstrations





• Ph.D. in Computer Science, Computational Linguistics, Applied Math or Statistics, Engineering, Bioinformatics, Physics, O.R., or related (strong math/stats background with an ability to understand algorithms and methods from both mathematical and intuitive viewpoints)

• At least six years of work experience focusing on Data Science / Machine Learning – at least four of these years specializing in NLP-related work.

• In-depth knowledge of various NLP domains such as entity extraction, speech recognition, topic modelling, machine translation, natural language understanding, parsing, question answering, etc

• Extensive experience using NLP related techniques/algorithms such as HMM, CRF, deep learning & recurrent ANN, word2vec/doc2vec, Bayesian modelling, etc

• Strong data extraction and processing skills and experience

• Experience with a programming language such as C++, Java, or python. Experience with data structures and algorithms and ability to work in a Unix environment, processing large amounts of data in a big data environment

• Have a strong passion to understand how things work and to make them work better;

• Be able to absorb a high volume of knowledge and data quickly;

• Be a very strong problem solver;

• Possess good written and verbal communications skills;

• Enjoy a fast-paced, high-intensity, cross-functional environment.

Desired Qualifications:

• Significant experience building robust data processing and analytics pipelines

• Success in building strong ontologies / taxonomies / other representation of institutional knowledge, and then leveraging these structures to solve a variety of business problems

• Experience with one or more modern Big Data technology stacks

BlackRock is proud to be an Equal Opportunity and Affirmative Action Employer. We evaluate qualified applicants without regard to race, color, national origin, religion, sex, disability, veteran status, and other statuses protected by law.

Educational level:

Ph. D.

Level of experience (years):

Senior (5+ years of experience)

How to apply:

Please mention NLP People as a source when applying


Tagged as: , , ,

About BlackRock

Global investment management.