Natural Language Processing Engineer Position at the IBI Group of GRIB

Deadline:
31/05/2020
Centre / Institution:
Hospital del Mar Medical Research Institute
Bioinformatics expertise:
Algorithmics, Biomedical Informatics, Text Mining
Keywords:
Text Mining; Natural Language; Machine Learning; semantics; Text Analysis; programming

Job description

The Integrative Biomedical Informatics group (IBI) led by Laura I. Furlong and Ferran Sanz at GRIB (IMIM-UPF) in Barcelona is an international research group characterized by a unique experience in the fields of Network Medicine and Biomedical Text Mining. Text Mining activities at IBI focus on the extraction and aggregation of biomedical and clinical knowledge from several types of textual sources including biomedical scientific literatureclinical notes and social media. Some relevant examples of application scenarios include: (i) mining genetic information on diseases from scientific articles, thus contributing to the population of the DisGeNET and PsyGeNET knowledge platforms; (ii) extracting toxicology information from legacy reports;  (iii) analyzing social media posts and user behavior to detect mental disorders; (iv) processing clinical notes to support and automate healthcare decision making and planning. Part of Text Mining research lines at IBI are carried out in the context of national and international research projects including eTRANSAFE, FAIRplus, EMIF, Open PHACTS, MedBioinformatics, iPiE, eTOX.

The successful candidate will be involved in applied research projects aiming at extracting structured biomedical knowledge from textual contents. She/he will participate in the design and development of Text Mining and Natural Language Processing tools and workflows tailored to analyze different types of texts in the context of different ongoing projects in the group. The selected candidate will contribute to the activities related to textual data collection as well as the implementation, tuning and evaluation of Natural Language Processing algorithms / Machine Learning models.

Desired skills and expertise

Required qualifications and skills

  • University degree in informatics, language engineering, bioinformatics or related area
  • Master or PhD degree is a plus
  • Strong programming skills in Python and/or Java
  • Experience in configuring and querying Database Systems, both SQL (e.g. MySQL) and NoSQL (e.g. MongoDB, Elasticsearch) and in Unix
  • Experience in working with source code repositories (e.g. Github, BitBucket, etc.)
  • Good English communication skills
  • Strong problem-solving skills applied to real world analytical problems and ability to communicate outcomes of analyses in clear and precise manner
  • Strong interpersonal skills
  • Ability to work in a multidisciplinary environment

Desirable qualifications and skills

  • Experience in one or more of the following areas: entity/relation extraction, information extraction, document classification, semantics, summarisation, question answering, knowledge graph
  • Knowledge of both classical and deep Machine Learning techniques (their application to text analysis scenarios is a plus)
  • Experience with NLP Toolkits / Libraries like GATE, UIMA, NLTK, text parsers, etc.
  • Experience with Machine Learning tools like scikit-learn and Tensorflow / Keras
  • Implementation of Text Analysis workflows and integration of Natural Language Processing tools
  • Knowledge of techniques and application frameworks useful to process large dataset (a plus)

Contract duration and other benefits

Annual full time contract with the possibility of extension. Salary to negotiate according the expertise of the candidate. This contract is funded by the Enhancing TRANslational SAFEty Assessment through Integrative Knowledge Management (eTRANSAFE) project, from the European Commission.

Required information and contact

To apply: Please send a CV to carina.oliver@upf.edu with Ref: IBI, letter of interest and the contact information for 2-3 referees.