Connecting to LinkedIn...

Data Scientist (NLP) | Antwerp | Contract

Job Title: Data Scientist (NLP) | Antwerp | Contract
Contract Type: Contract
Location: Mechelen, Antwerp
Industry:
Salary: Negotiable
Start Date: ASAP
Duration: 12
REF: RE3_1516293007
Contact Name: Rueben Schreur
Contact Email: Rueben.Schreur@parallelconsulting.com
Job Published: 5 months ago

Job Description

The Data Scientist

You are responsible for research, design, experimentation, implementation, validating and testing data science models for trademark similarity searching. He/she works in the 'model engineering / data science team' in close cooperation for technical implementation and integration with the 'search technologies' team, for knowledge acquisition and model verification with subject matter experts from trademark operations, for product design and validation with product management.


Research, design and implementation of data science solutions to address trademark similarity and relevancy model challenges, covering the full range of similarity scoring models, underlying NLP-related and patternmatching models, data linkage models and machine learning models.


Solution design, implementation and validation of components/libraries/services for string matching, computational linguistic components on phonetics, inflections, term tagging, semantic/conceptual similarities, etc.

Execution of corpus analysis, statistical data analysis and machine learning to compose knowledge sources for computational matching and data linkage.

Design and execution of machine learning applications for similarity classification, text mining, entity recognition, topic classification, word embedding etc.

Definition and execution of validation cycles with subject matter experts to measure precision/recall and identify areas for improvement.

Analytics of data capturing internal analyst knowledge work (e.g. citations of most relevant marks).Analytics and behavioral segmentation of captured client knowledge work (e.g. screening and citations on online platform)

Information retrieval analysis and implementations; either using and adapting frameworks (e.g. ElasticSearch/Lucene), either design and implementation of core models (e.g. vector space models, LSI/LDA, finite state machine for regular expression matching, etc.) Correctness and Performance testing of data science components and systems. Knowledge representation and knowledge distribution. Support and knowledge distribution of data science applications to internal analysts and/or clients.

Follow-up of data science / technical research domain, aligned with the IT research goals and methodologies.

Education:
MSc degree in Computer Science, Mathematics or related field
PhD or additional MSc in Computer Science, Artificial Intelligence, Statistics, Computational Linguistics or related field, (or alternatively 5+ years relevant industry experience in building data science applications).

Experience:

Experience with hands-on development of data science solutions in one or more of the following data science fields:
o knowledge representation, knowledge bases and reasoning models, inferencing engines
o statistical data analysis
o probabilistic models, graph models
o applied machine learning (supervised/unsupervised, decision trees, neural networks, ensemble methods, genetic algorithms/programming)
o natural language processing, text mining, corpus analysis o information retrieval
o topic classification (vector space, LSI/LDA, ..), word-embedding (word2vec, GloVe, ...), etc.
o semantic networks / ontologies
* Experience with software development
* Experience with data analysis and experimental design
* Experience with database technologies, large dataset processing

Other Knowledge, Skills, Abilities or Certifications:

o proficient programming skills in a high-level language (core Java, Scala, ..)
o knowledge on data analysis and experimental design (R, iPython, ..)
o knowledge of relational databases, noSQL and Memory database technologies, graph processing (MongoDB,
Redis, Memcached, Spark/GraphX, Neo4J, ..)
o broader knowledge and experience with large dataset processing and distributed computing architectures.
(Spark/Hadoop architectures)


12 month + project.
Interviews immediate.

If you're interested please respond with you CV and desired rate!

have a great day!

Parallel Consulting is acting as an Employment Business in relation to this vacancy.