Data Scientist - NLP

Job Summary

To support long-term federal client engagements, the full-time remote Data Scientist - NLP will apply statistical programming, modeling, visualization techniques, and data mining skills to analyze complex public sector challenges.

Key responsibilities:

• Collect, clean, and prepare data sets for computational modeling using Python, including pre-processing techniques like stop word removal and tokenization
• Demonstrate experience with NLP feature engineering methods and select classification modeling techniques to address business problems
• Present modeling results and insights, explaining their relevance to organizational challenges

Required qualifications:

• Master's degree required, PhD preferred in Statistics, Mathematics, Computer Science, or a related field
• At least four years of experience developing scalable, production-ready NLP solutions using tools like sci-kit learn, Keras, and TensorFlow
• High proficiency in SAS, R, or Python for NLP applications such as Document Summarization and Sentiment Analysis
• Experience with open-source NLP packages such as Gensim, SpaCy, or NLTK
• Must be a US citizen and able to obtain and maintain a Public Trust security clearance