Senior Data Scientist

Securiport Llc
Reston, VA, United States
about 2 months ago
Apply on www.indeed.com
Prepare application

Role details

Contract type
Permanent contract
Employment type
Full-time (> 32 hours)
Experience level
Expert
Experience required
5 years minimum
Working hours
Regular working hours
Job source

Tech stack

Airflow BigQuery Cloud Database Data Integration Data Security Data Structures Data Systems Monitoring of Systems Python (Programming Language) Machine Learning Operational Data Store Standard Sql
+9 more
Workflow Management Systems Snowflake Pandas Scikit Learn Data Lineage Data Analytics Software Version Control Data Pipelines Amazon Redshift

Job description

The Senior Data Scientist owns the analytics engine behind KIBO’s service - the price-verification benchmarking and the risk-scoring that turn import-declaration data and international trade data into defensible, inspection-ready outputs and the reporting delivered to the customs administration. It is the pivotal quantitative role, and includes building the customs-revenue baseline analysis that underpins the program., * Data integration. Build and maintain pipelines that ingest customs declaration data (ASYCUDA/SYDONIA) and commercial international trade-price data, reconciling schemas, units and currencies into a single analytical warehouse.

  • Price-verification analytics. Construct the benchmarking that compares declared values against international reference prices - surfacing likely under-invoicing while respecting the WTO Customs Valuation framework - and document the method so findings are defensible.
  • Risk scoring. Design, train and monitor the models and rules that score declarations for anomalies in value, tariff classification and origin, and that prioritize shipments for inspection.
  • Revenue-baseline analysis. Produce the customs-revenue baseline analysis used to establish reference metrics with the authorities.
  • Generate the recurring risk-assessment reports and the monthly reporting delivered to the customs administration, with clear, auditable lineage from source data to conclusion.
  • Feedback loop. Incorporate field-inspection results back into the models to improve hit-rates over time., * Stand up the analytical environment and ingest initial customs and trade-data samples.
  • Deliver an initial customs-revenue baseline analysis and prototype the price-verification benchmarking and risk-scoring.Produce the first risk-assessment reports that support inspection getting under way.

Reporting and Working Relationships

Reports to the Engagement / Delivery Lead; takes valuation-methodology guidance from the Customs & Valuation Subject-Matter Expert; partners with the Senior Full-Stack Developer on data access and tooling; consumes inspection results from the field via the Technical Manager and Data & IT Liaison., * High-impact, mission-driven work supporting the modernization of a national customs administration.

  • The opportunity to help design a platform with long-term economic, operational, and public-sector impact.
  • A collaborative, multidisciplinary team of customs, technology, data, and engineering specialists.
  • Significant ownership and influence during a critical program build-out phase. Opportunities for professional growth as the platform and program expand. *

If you are motivated by mission-driven work and want to help establish the architecture behind a transformative customs-modernization program, we encourage you to apply.

KIBO Laboratories LLC is an equal-opportunity employer and welcomes qualified applicants of all backgrounds. Offers are contingent on background, right-to-work and - where applicable - sanctions-screening checks.

Requirements

  • 5+ years of experience in data science, quantitative analytics, applied statistics, or machine learning, including production experience building models and data pipelines using real operational data.
  • Strong Python and SQL skills, with hands-on experience using tools such as pandas, scikit-learn, or equivalent analytical/modeling libraries.
  • Experience with anomaly detection, statistical benchmarking, supervised or unsupervised modeling, model monitoring, and performance evaluation.
  • Demonstrated ability to work with large transactional, logistics, financial, trade, or similarly complex operational datasets, including reconciling heterogeneous sources, schemas, units, and currencies.
  • Ability to clearly document analytical methods, explain findings, and defend quantitative outputs to non-technical stakeholders, auditors, or government counterparts.Strong data-governance practices, including reproducibility, data lineage, version control, quality checks, and appropriate handling of sensitive data. *, * Exposure to customs, international trade, tariff/HS classification, import/export data, valuation, or commercial trade-price data.

  • Familiarity with ASYCUDA/SYDONIA data structures or other customs, logistics, or government data systems.
  • Experience standing up analytics capabilities in data-constrained, emerging-market, public-sector, or operationally complex environments.
  • Experience with cloud data warehouses and workflow orchestration tools such as Snowflake, BigQuery, Redshift, Airflow, dbt, Prefect, or similar platforms.#LI-NA1 *

Benefits & conditions

  • Competitive compensation and a comprehensive benefits package.

About the company

KIBO is a registered United States company dedicated to providing governments worldwide its services of inspection, analysis, certification, and compliance.

Apply for this position

This job is hosted externally. Click below to view the full posting and apply.

Apply on www.indeed.com
Prepare application

Good distractions

Talks and stories from around this role — technically off-topic, practically not.

2:15 min

Empowering domain teams with an open data platform

Sandhya Menon Sandhya Menon · World Congress 2026 Europe

2:03 min

Accelerating pandas dataframes using cudf module plugins

Ankit Patel Ankit Patel · World Congress 2024

2:30 min

Leveraging BigQuery ML for scalable SQL-based segmentation experiments

Julian Joseph · LIVE

3:09 min

Balancing data science skillings alongside systems engineering rigor

Nico Schmidt · LIVE

3:33 min

Refactoring data science workflows using Rapids QDF and Pandas

Paul Graham Paul Graham · LIVE

6:58 min

Analyzing production code coverage data using pandas

Markus Harrer Markus Harrer · World Congress 2021

Videos

See all

Related articles

See all