Data Scientist – Public Trust Required

Data Scientist — Entity Resolution / Record Linkage | Public Trust Required

Location: Woodlawn, MD

Work Model: 100% Onsite — 5 Days/Week

Employment Type: W2

Experience: 10+ Years

Compensation: $80–$100/hour W2

Clearance: Public Trust Required / Must Be Eligible to Obtain

Job Summary

We are seeking an experienced Data Scientist with 10+ years of IT experience and strong expertise in Entity Resolution, Record Linkage, NLP, Python, and Advanced SQL .

The ideal candidate will have hands-on experience building data processing and record-matching solutions that identify, link, cleanse, and deduplicate records across large and complex datasets.

Key Responsibilities

• Design, develop, and maintain advanced data processing and entity resolution pipelines using Python and SQL.

• Apply NLP and information extraction techniques including Named Entity Recognition (NER), blocking and indexing, string distance metrics, TF-IDF, cosine similarity, phonetic encoding, and address standardization .

• Clean, transform, validate, and manage large-scale datasets from diverse sources.

• Develop solutions focused on data quality, integrity, security, and privacy.

• Write and optimize complex SQL queries and database operations for performance and scalability.

• Perform data validation, testing, deployment, and post-implementation monitoring.

• Participate in code reviews and follow version-control and reproducibility standards.

• Develop and maintain reliable, scalable data pipelines.

• Translate complex matching algorithms, thresholds, and probabilistic scoring into understandable business logic.

• Communicate technical findings and recommendations effectively to both technical and non-technical stakeholders.

Required Qualifications

• 10+ years of IT industry experience.

• Bachelor’s degree in Statistics, Applied Mathematics, Computer Science, Information Science , or a related field.

• Strong hands-on experience with Entity Resolution, Record Linkage, and Deduplication .

• Deep practical knowledge of NLP and information extraction .

• Experience with:

• Named Entity Recognition (NER)

• Blocking and indexing

• String distance metrics

• TF-IDF

• Cosine similarity

• Phonetic encoding

• Address standardization

• Hands-on experience with Splink, FastLink, Dedupe, or recordlinkage .

• Strong Python programming and data-pipeline development skills.

• Advanced SQL skills, including complex queries and optimization.

• Strong Regex skills for data cleansing and pattern matching.

• Experience with spaCy and scikit-learn .

• Strong written and verbal communication skills.

Preferred Qualifications

• Experience working with federal, state, or local government data .

• Experience with PostgreSQL, DB2, Oracle, SQL Server, Hadoop, and flat files .

• Experience with Jenkins and CI/CD .

• Experience with data pipeline scheduling, automation, and monitoring tools.

• Experience owning data pipeline architecture from data discovery through production and post-implementation .

Public Trust Requirement

The selected candidate must be eligible to obtain and maintain a Public Trust suitability determination and successfully complete the required federal background investigation.

Previous Public Trust or federal clearance/suitability experience is highly preferred.

Work Location

This is a 100% onsite position in Woodlawn, Maryland, Monday through Friday .

The position is not remote or hybrid . Candidates must currently live within reasonable commuting distance or have a firm relocation plan before starting the position.

Relocation assistance is not provided.

Employment Requirements

• W2 employment only

• Must be legally authorized to work in the United States

• Must be able to work on W2 without sponsorship or transfer