Sr Data Scientist

Job Description

Strong practical experience with Natural Language Processing (NLP), Text Processing, and Information Extraction concepts including Named Entity Recognition, Blocking and Indexing, String Distance Metrics, TF-IDF/Cosine Similarity, Phonetics Encoding, Address Standardization

Solid Python, Regex, and SQL experience

Excellent Communication skills

Position Description
Develop Analytics Solutions: Design, implement, and maintain advanced data processing and entity resolution pipelines using Python and SQL on enterprise data platforms.

Data Management: Clean, transform, and manage large-scale datasets from diverse, complex sources, ensuring absolute data integrity, reliability, and security.

Performance Optimization: Optimize complex SQL queries and database operations to ensure efficient data access, processing, and scalability.

Engineering Standards: Actively participate in code reviews, enforce version control, and uphold best practices for code quality, reproducibility, and data privacy.

End-to-End Delivery: Support data validation, testing, deployment, and post-implementation monitoring in a fast-paced environment.

Detailed Skills Requirements
Foundation for Success (Basic Qualifications)
Bachelor's degree in Statistics, Applied Mathematics, Computer Science, or Information Science with experience in NLP, Text Processing, Information Extraction, Python, SQL, Regex and specialized libraries/frameworks.

Overall 10+ years' experience in IT industry

Factors To Help You Shine (Required Skills)

**Selected candidate must be able to obtain and maintain a public trust clearance**

• *Selected candidate must be willing to work on-site in Woodlawn, MD 5 days a week**
• *Master's and 10+ years of experience, Bachelor's and 12+ years of experience or 18+ years in lieu of a degree**

Strong practical experience with Natural Language Processing (NLP), Text Processing, and Information Extraction including:

Practical knowledge of Named Entity Recognition and Address Standardization to extract and clean unstructured text data.

Deep understanding of data matching strategies, including Blocking and Indexing, String Distance Metrics, and Phonetic Encoding.

Experience applying TD-IDF and Cosine Similarity for text comparisons and information retrieval.

Strong Python development skills for building analytics solutions and manipulating data.

Advanced SQL proficiency for complex data querying, optimization, and database operations.

Practical experience using Regex for advanced text processing, data cleansing, and pattern matching.

Familiarity with specialized libraries and frameworks including:

Linkage libraries such as Splink / FastLink, Dedupe, or record linkage

Core Python data science libraries, specifically spaCy for NLP tasks and Scikit-Learn for general machine learning and clustering

Familiarity with code reviews, version control, and maintaining data security and reproducibility standards.

Excellent communication skills.

How To Stand Out From The Crowd (Desired Skills)
Prior experience delivering IT or data initiatives within federal, state, or local government environments

Proven ability to operate independently, take ownership of data pipeline architectures, and drive projects from data discovery through to post-implementation.

Experience retrieving, migrating, and manipulating data from legacy and distributed systems, including PostgreSQL, DB2, Oracle, SQL Server, and Hadoop, as well as unstructured flat files.

Experience utilizing Jenkins to automate continuous integration, testing, and deployment (CI/CD) for data validation pipelines.

Experience with pipeline automation tools to schedule and monitor complex data cleansing jobs.

Strong ability to translate complex algorithmic decisions (such as probabilistic match thresholds) into clear business logic for executive leadership and non-technical stakeholders.

Excellent problem-solving skills and proven verbal/written communication skills when collaborating across cross-functional teams.