Senior Data Scientist - Entity Resolution and NLP
ETHOS - Talent & AdvisoryAbout the role
If you have spent your career making messy data agree with itself, this is your kind of problem.
What You Will Do
You will design, build, and maintain the entity resolution and advanced data processing pipelines that decide when two records refer to the same real world entity, working in Python and SQL on large enterprise data platforms. Day to day, that means cleaning and transforming high volume datasets drawn from diverse and complicated sources, tuning complex SQL and database operations so the work stays fast as it scales, and defending data integrity, reliability, and privacy at every step. You will participate in code reviews, hold the line on version control and reproducibility standards, and stay with your work through validation, testing, deployment, and post implementation monitoring. You will also be the person who explains what a probabilistic match threshold actually means to people who do not write code.
What You Need
Master's degree with 10+ years of experience, Bachelor's degree with 12+ years, or 18+ years of experience in lieu of a degree
Degree, where applicable, in Statistics, Applied Mathematics, Computer Science, or Information Science
Ability to obtain and maintain a federal Public Trust clearance
Willingness to work onsite 5 days per week
Strong practical experience across Natural Language Processing, text processing, and information extraction, specifically:
Named Entity Recognition and address standardization for extracting and cleaning unstructured text
Data matching strategy including blocking and indexing, string distance metrics, and phonetic encoding
TF-IDF and cosine similarity applied to text comparison and information retrieval
Strong Python development skills for building analytics solutions and manipulating data
Advanced SQL for complex querying, optimization, and database operations
Practical Regex for advanced text processing, data cleansing, and pattern matching
Familiarity with linkage libraries such as Splink, FastLink, Dedupe, or recordlinkage
Working fluency in spaCy for NLP and scikit-learn for machine learning and clustering
Familiarity with code review, version control, data security, and reproducibility standards
Excellent written and verbal communication skills
What Makes You Stand Out
Prior delivery of IT or data initiatives in a federal, state, or local government environment
A track record of operating independently and owning a data pipeline architecture from discovery through post implementation
Experience pulling and migrating data from legacy and distributed systems including PostgreSQL, DB2, Oracle, SQL Server, and Hadoop, plus unstructured flat files
Jenkins for automated CI/CD on data validation pipelines
Pipeline automation tooling to schedule and monitor complex data cleansing jobs
The ability to translate algorithmic decisions such as match thresholds into clear business logic for executive and non technical stakeholders
Responsibilities
- Design, build, and maintain entity resolution and data processing pipelines
- Clean and transform high volume datasets from diverse sources
- Tune complex SQL and database operations for performance
- Participate in code reviews and maintain version control standards
- Explain probabilistic match thresholds to non-technical stakeholders
Qualifications
- Master's degree with 10+ years of experience or Bachelor's degree with 12+ years
- Degree in Statistics, Applied Mathematics, Computer Science, or Information Science
- Ability to obtain and maintain a federal Public Trust clearance
- Strong experience in Natural Language Processing and text processing
- Proficient in Python and advanced SQL
Skills mentioned
About ETHOS - Talent & Advisory
ETHOS - Talent & Advisory is a multifaceted talent advisory firm renowned for its comprehensive services in Executive Search, HR Consulting, Growth Strategy, and Diversity, Equity, and Inclusion (DEI). With a mission to transform organizations through exceptional talent solutions, ETHOS is your trusted partner in achieving success. In the realm of Executive Search, we specialize in identifying and securing top-tier executive talent that aligns seamlessly with your organization's vision and values. Our rigorous and personalized approach ensures that you have the right leaders driving your company towards excellence. Our HR Consulting services are designed to optimize your workforce strategies. We provide expert guidance on HR processes, talent management, and organizational development, enabling you to build a high-performing and engaged workforce. ETHOS's Growth Strategy expertise empowers organizations to expand, innovate, and thrive in dynamic markets. We collaborate closely with you to devise growth plans that exceed targets, ensuring your continued success. Diversity, Equity, and Inclusion are at the core of our values. We bring extensive experience and deep commitment to DEI initiatives, helping you create inclusive workplaces that drive innovation and sustainable growth. At ETHOS, our commitment to quality, client culture alignment, and our holistic approach to talent solutions sets us apart. We are not just a service provider; we are your dedicated partner in shaping a brighter future for your organization.
H-1B sponsorship history
Historical employer filing data was found for ETHOS - Talent & Advisory. The employer record includes 78 historical certified applications. This is employer-level history, not a guarantee that this role currently offers sponsorship.