ME00647-Data Scientist 3
Momentum Engineering, Inc. · Fort Meade, Maryland, United States · $135K–$180K/yr
Software Development · 11-50 employees
About the role
The Data Scientist will develop and improve NLP solutions for processing spoken and written language data, including automated tokenization and linguistic annotation. They will also evaluate model performance against human-generated annotations and document analytical methods.
What they look for
Requirements
Candidates must possess an active Top Secret/SCI clearance with an NSA Full Scope Polygraph and a minimum of a Bachelor's degree with 8 years of relevant experience. Proficiency in NLP, tokenization, and software development is required.
Benefits
Full description
Job Summary
- Seeking a Data Scientist to support a Natural Language Processing project focused on automatically processing spoken and written language data
- The successful candidate will develop automated tokenization and linguistic annotation capabilities and evaluate model performance against human-generated annotations
Primary Responsibilities
- Develop NLP solutions for spoken and written language data
- Develop automated approaches for accurate language tokenization
- Create automated solutions for annotating language data with parts-of-speech information
- Analyze speech and text datasets
- Improve existing NLP models and processing techniques
- Evaluate model performance against human-generated annotations
- Develop quantitative methods for measuring model accuracy and effectiveness
- Document model performance, analytical methods, and recommended improvements
Required Qualifications
- Must have active Top Secret/SCI clearance with NSA Full Scope Polygraph
- Master’s degree with 6 years of relevant experience, Bachelor’s degree with 8 years of relevant experience, Associate's degree with 10 years of in-depth relevant experience that is clearly related to the position
- Experience with Natural Language Processing
- Experience processing text and/or speech data
- Experience developing automated language-processing solutions
- Understanding of tokenization and linguistic annotation concepts
- Experience evaluating model performance
- Strong analytical and software-development skills
Desired Qualifications
- Experience with parts-of-speech tagging
- Computational linguistics background
- Experience evaluating automated NLP output against human-generated annotations
- Experience working with both speech and text datasets
Exempt hourly position. 11 paid holidays, minimum of 3 weeks PTO, company sponsored group medical plan, company paid dental, vision, life insurance, and STD/LTD plans. Salary is dependent upon the candidate’s experience and qualifications.
