NLP Data Scientist



  • The SyTrue Data/Research Scientist would be working with the SyTrue R&D, Data
    Science and Clinical team to analyse clinical records and design new algorithms
    specially to achieve different NLP tasks. Current NLP research tasks includes
    improvement of Named Entity recogniser, Multi-class Document Classification and
    Clinical Document Segmentation.
  • Research and identify features from Clinical Narration. Create Multiple POC with
    different NLP libraries.
  • Work independently creating and assessing their rules using SyTrue’s proprietary
    integrated rules engine framework.
  • Creation, modification, and maintenance of medical data extraction models and
  • Test new tools, models and utilities that are to be integrated into the platform.
  • Translate the customer’s needs to needed rules or models. Handle updates, additions
    and maintenance.
  • Assist customers with troubleshooting data errors, support calls/tickets and training
    as needed.
  • Ownership of End-to-End Clinical Data Analysis, Proof of concept, development,
    deployment and maintenance of models.
  • Communicate and present various proposals, findings, and results to clinical
    collaborators, stakeholders and customers.

Minimum qualifications:

  • Bachelor’s Degree in Computer Science, Information management, Statistics or
    related field, with some experience and interest to grow in the Healthcare data
    analytics industry.
  • Knowledge of any cloud environment. Hands-on experience and ability to translate
    algorithms/models into commercially viable products or services and deploy it.
  • Having implementation and deployment level knowledge in Supervised and
    Unsupervised learning algorithms using Neural networks and Deep-Learning (NLP
    utilising RNN, CNN, LSTM, Transformers, Attention Models, Language models,
    Transfer Learning).
  • Language Tools/Library: Python, NLTK, TensorFlow 2, PyTorch or Keras, Gensim,
  • Medical Terminology Knowledge of either ICD 9, ICD 10 or SNOMED or Healthcare
    Background or Medical coding knowledge.

Preferred qualifications:

  • Master’s degree or PhD in Computer Science, Information management, Statistics or
    related field.
  • Research Publication(s) in reputed Conferences and Journals.
  • Ability to research and solve open ended clinical data processing problems.
  • Healthcare/Clinical data analysis and Terminology Knowledge of ICD 9, ICD 10 and

Personal/Business Traits:

  • Research Oriented, Self-driven and detail-oriented, able to take ownership of Data
    Science and other assigned projects.
  • Comfortable working in remote culture (WFH) and with minimal supervision.

To apply for this job email your details to

Skip to content