NLP Engineer

About Burning Glass

At Burning Glass Technologies, we strive to create a job market that works for everyone. We are an analytics software company whose tools play a growing role in informing the global conversation on education and the workforce by turning data into insight. Powered by the world’s largest and most sophisticated database of jobs and talent, we deliver real-time data and breakthrough planning tools that inform careers, define academic programs, and shape workforces.

Analytics are at the heart of our mission, and our Analytics team plays a critical role in delivering insights for our products and clients from hundreds of millions of job postings and resumes. The team is responsible for developing models for classifying, validating, and understanding the job market data in our software products; ensuring and maintaining data quality; and creating reports which analyze areas of the labor market that are critical to our clients and partners. Our team’s technology stack includes Python and R for data science and analysis, and SQL Server, ElasticSearch, and MongoDB for managing and working with our large datasets.

About the Position

We seek an experienced NLP Engineer to work on a range of initiatives related to applying natural language processing algorithms to parse structured and unstructured job market data as well as applying parsed data in various applications such as semantic similarity, content tagging and multi-label classification problems. Our products are used across the global job market: by students and workers to fulfill future career goals, by educators to align programs with the market, and by employers to in fill positions more effectively.

Key Responsibilities:

  • Apply NLP/ML algorithms on labelled/unlabeled job market data in various applications such as text classification, document tagging etc.
  • Training machine learning models in both data rich and data poor circumstances, so feature engineering using domain knowledge will be important, and also using both supervised and semi-supervised techniques.
  • Perform data and error analysis in order to improve models and understand their shortcomings.
  • Apply machine learning algorithms on rule based systems to improve scalability and performance metrics.
  • Work alongside the engineering team to scale and implement the developed solutions in production.



  • Experience with structured and unstructured data including natural language processing techniques.
  • Familiarity with NLP toolkits such as Scikit-learn, numpy, scipy, R, Weka, NLTK, Stanford CoreNLP.
  • Familiarity with information retrieval, NLP, topic modeling, and/or semantic vector spaces.
  • Highly proficient in Python and SQL. Experience with MongoDB, ElasticSearch, and Neo4j preferred.
  • Practical industry experience in applying one or more core Machine Learning methodologies: Regression, Classification, Clustering, Matrix Factorization, Predictive Analytics, Decision trees, Support Vector Machines, Neural Networks/ Deep Learning.
  • Experience working with large data sets and distributed computing tools a plus (Map/Reduce, Hadoop, Hive, Spark, etc.)
  • Exceptional ability to communicate findings to technical and non-technical audiences.
  • 3+ years of related experience.
  • MS in Computer Science or related field or equivalent industry experience.


Competitive salary, commensurate with experience, and comprehensive benefits package offered. To apply, please send your resume and cover letter to