FactSet is seeking a Senior Data Scientist with significant experience in natural language processing and knowledge graph development, including experience building and/or prototyping KGs and application of machine learning to knowledge graphs. This role is located within the Content Engineering AI team and reports to the VP, Director of AI.
The Senior Data Scientist works with Director of AI to develop a roadmap for management and growth of information systems to improve entity, topic, and relationship definition, extraction, and normalization from unstructured text.
Work may include entity and topic modeling, semantic tagging/enrichment, information extraction, transfer learning, and graph neural networks.
Python data science stack and Jupyter Notebooks (Pandas, Scikit learn, Numpy, Networkx, etc.)
Development and design of ontologies / taxonomies for knowledge bases
Prior experience with RDFs, triple stores, and relation extraction
Experience with classifiers and embeddings for knowledge representations
3+ years experience in development of Machine Learning or NLP programs and classification algorithms
Experience with NLP libraries (e.g. NLTK, SpaCy)
Development of linear models or classifiers for reporting and analytics (e.g. regression, Bayesian classifiers, random forest, SVM)
Prior experience working with unstructured data (text content, JSON records) including feature engineering experience from unstructured data
Working with Agile development practices in a production environment
MS in Machine Learning, Computer Science or a related discipline to come up with ideal solutions for challenging problems.
Graph database experience (AWS Neptune, Neo4j)
Experience or exposure with AWS environment [SageMaker, S3, Athena, Glue, ECS, EC2]
Experience working with large volumes of data in a stream or batch processing environment.
Prior experience with Docker and API development
Familiarity with deep learning libraries (Keras, PyTorch, Tensorflow)
Usage of MongoDB
Familiarity with big data tool chain (e.g. Pyspark, Hive)
FactSet is an Equal Opportunity Employer - M/F/Veteran/Disability/Sexual Orientation/Gender Identity
Factset Research Systems Inc.