Data Scientist/Engineer - Natural Language Processing

We are looking for an experienced machine learning / natural language processing data scientist to join a new and exciting team focused on delivering advanced analytics solutions in the electronic discovery and compliance industry. The advanced analytics team is at the center of providing insights and predictions in support of new strategic offerings and products, bringing real value to our clients through analysis of data.  

You will have a proven track record of being able to tackle tough problems, bringing the right algorithmic solutions to large data sets, ensuring that any solution accurately fits the business problem at hand. As important is the ability to work as part of a growing team, being open-minded across a range of problems and techniques and a willingness to learn from and contribute to the team. 

Position Description – Data Scientist (Natural Language Processing) 

Responsibilities 

Develop 

robust, scalable and maintainable machine learning models 

to answer business problems against large data sets 

Build methods for document clustering, topic modeling, text classification, named entity 

recognition, sentiment analysis, and POS tagging 

Perform elements of data cleaning, feature selection and feature engineering and organize experiments in conjunction with best practices 

Benchmark, apply, and test algorithms against success metrics. Interpret the results in terms of relating those metrics to the business process 

Work with development teams to ensure models can be implemented as part of a delivered solution replicable across many clients 

Visualize data to tell compelling stories 

Requirements 

3 + years’ experience with Machine Learning, NLP, Document Classification, Topic Modeling and Information Extraction with a proven track record of applying them to real problems and real data 

Experience working with big data systems and big data concepts 

Ability to provide clear and concise communication both with other technical teams and non-technical domain specialists 

Strong team player; ability to provide both a strong individual contribution but also work as a team and contribute to wider goals is a must in this dynamic environment 

Experience with noisy and/or unstructured textual data 

Strong coding ability with statistical analysis tools in Python or R, and general software development skills (source code management, debugging, testing, deployment, etc.) 

Working knowledge of various text mining algorithms and their use-cases such as keyword extraction, PLSA, LDA, HMM, CRF, deep learning & recurrent ANN, word2vec/doc2vec, Bayesian modeling 

Strong understanding of text pre-processing and normalization techniques, such as tokenization, POS tagging and parsing and how they work at a low level. 

Excellent problem solving skills. 

Strong verbal and written communication skills 

Practical experiences in using NLP related techniques and algorithms 

Proven track record of analyzing data and bringing value across a range of projects 

Experience in Greenplum and MadLib highly desirable 

Experience in open source coding and communities desirable 

Education 

Masters or 

higher in data mining or machine learning; or equivalent practical analytics / modelling experience