Senior Data Scientist

We are a federal IT company on a mission to make customer experience (CX) the center of every government solution.
Technology is our Passion. People are our Purpose.

We know tech, but we love people. NuAxis is home to thinkers and feelers; engineers and artists. We work hard and support each other along the way. Teamwork is more than just a buzzword for us, it's a state of mind.

Full-Time

The Senior Data Scientist will be responsible for analyzing, cleansing, reconciling, and statistically validating complex datasets related to wildlife trade, permits, applicants, species, transactions, shipments, and historical records. The role will focus heavily on data quality, entity resolution, anomaly detection, taxonomy reconciliation, and the development of reliable, standardized datasets for downstream analytics and reporting. The ideal candidate will have strong experience working with large, complex, and legacy datasets and will be comfortable developing reproducible analytical solutions using Python, SQL, and preferably R.

• Analyze and cleanse complex structured and unstructured datasets from multiple sources.
• Identify malformed, irrelevant, incomplete, and corrupted free-text records and extract usable structured information.
• Standardize and map data values to established controlled vocabularies and master-data standards.
• Reconcile species identifiers, scientific names, common names, and related taxonomy information.
• Resolve synonyms, misspellings, deprecated names, taxonomy inconsistencies, and other data discrepancies.
• Standardize units of measure, quantities, country codes, source codes, and other data attributes.
• Perform deterministic and probabilistic record linkage across multiple datasets.
• Apply fuzzy matching and similarity techniques to identify related records.
• Identify duplicate applicants, permits, transactions, shipments, and other business entities.
• Develop reversible and auditable entity-resolution and entity-merging methodologies.
• Design and implement statistical methods for anomaly and outlier detection.
• Analyze cross-source consistency, completeness, accuracy, and reliability.
• Develop data-quality rules, validation checks, metrics, and scorecards.
• Establish measurable data-quality thresholds and monitor data-quality trends.
• Measure model and data-matching performance using labeled datasets, including precision and recall.
• Support the validation and certification of Gold-layer datasets.
• Develop reproducible Python and/or R analytical code and SQL queries.
• Document data-cleansing, reconciliation, matching, validation, and quality-assurance methodologies.
• Collaborate with data engineers, analysts, subject-matter experts, and project stakeholders to resolve complex data-quality issues.
• Provide recommendations for improving data standards, governance, and long-term data integrity.

• 7-10+ years of experience in data science, data quality, data analytics, or a related field.
• Strong experience working with complex, large-scale, and/or legacy datasets.
• Strong programming experience with Python and SQL
  .
• Experience with R is preferred.
• Hands-on experience with entity resolution, record linkage, duplicate detection, or master-data management.
• Experience implementing deterministic, fuzzy, and probabilistic matching techniques.
• Strong understanding of statistical analysis, anomaly detection, and outlier identification.
• Experience developing data-quality rules, validation frameworks, metrics, and scorecards.
• Experience working with controlled vocabularies, reference data, and standardized coding systems.
• Strong experience with data cleansing, transformation, normalization, and reconciliation.
• Experience evaluating analytical results using labeled datasets and measures such as precision and recall.
• Ability to develop reproducible, maintainable, and well-documented analytical code.
• Strong analytical, problem-solving, and communication skills.

• Experience working with scientific, environmental, biological, ecological, or taxonomy-related datasets
  .
• Knowledge of wildlife trade data, species identification, scientific nomenclature, or biological taxonomies.
• Experience resolving scientific names, synonyms, deprecated classifications, and taxonomy mismatches.
• Experience with large-scale legacy-data remediation and historical data conversion.
• Experience supporting data certification or Gold-layer data products.
• Familiarity with data governance, master-data management, and enterprise…