Journeyman Data Scientist (two positions)

INNOVIM•,

1d•$125,000 - $155,000•Hybrid

About The Position

This position supports a potential Department of the Air Force opportunity and is contingent upon contract award, final Government requirements, and candidate qualification and clearance verification. This posting does not represent an offer of employment and does not imply that a contract has been awarded or that any offeror has been selected. IDS is building a candidate pipeline for data scientists supporting a federal applied research program in acquisition cost analytics. The lead journeyman position builds and maintains the automated data pipelines, feature engineering, model tuning, and visualizations that the research depends on. The customer designates this position as key personnel, so qualification thresholds and clearance status are verified before any candidate is proposed. More than one seat is expected.

Requirements

Minimum five years of data science experience.
Proficiency in Python and R, including data manipulation libraries and machine learning frameworks, for exploratory analysis and model building.
Competence developing and maintaining data pipelines, with knowledge of extraction, transformation, and loading processes and frameworks.
Advanced knowledge of Databricks or an equivalent platform for efficient data collection, transformation, and loading.
Skill presenting findings using visualization tools such as Tableau or Power BI.
Experience working with diverse teams and translating data driven insight into actionable recommendations.
Active Secret clearance.
United States citizenship required.

Nice To Haves

Experience with Apache Spark and cloud based data warehousing.
Exposure to federal acquisition, financial, or program management data.
Experience working inside a government authorized cloud environment.

Responsibilities

Develop and maintain automated data pipelines, including extraction, transformation, and loading processes over large and heterogeneous source data.
Implement automated data quality checks, validation rules, error handling, and logging.
Build and maintain metadata tagging and data lineage so that any analytical result can be traced to the source record behind it.
Maintain all pipeline code, configuration, and infrastructure-as-code in a government version control repository, with documentation sufficient for independent redeployment.
Improve existing models through hyperparameter tuning, cross validation, and feature engineering.
Build dashboards and visualizations that communicate analytical findings clearly.
Work across a mixed team of cost analysts and engineers, translating analytical results into recommendations.