Data Scientist

Leidos

3d•$69,550 - $125,725

About The Position

The Enterprise Transformation Office is seeking a skilled Data Scientist with deep expertise in ETL (Extract, Transform, Load) pipeline development and process mining to join our Business Process Reengineering team. In this role, you will serve as the primary data engineer and analyst responsible for extracting and integrating data from a broad range of enterprise systems, applications, and databases, and loading it into our IBM Process Mining platform to enable accurate, actionable process models. This is an iterative, high-impact role: once an initial process model is produced, you will collaborate with process analysts and stakeholders to identify data gaps, refine extractions, and rebuild models to continuously improve fidelity. You will also work with task mining outputs, including desktop event logs, to supplement process discovery efforts.

Requirements

Bachelor's degree in Data Science, Computer Science, Information Systems, Statistics, or a related technical field.
3+ years of experience in ETL development, data engineering, or data integration roles.
Proficiency in SQL for complex querying, joins, and data transformation across multiple relational database platforms (SQL Server, Oracle, MySQL, PostgreSQL).
Experience with Python or R for data manipulation, scripting, and automation (pandas, NumPy, SQLAlchemy, etc.).
Demonstrated experience working with event logs, transaction logs, or time-series data in an analytical context.
Familiarity with process mining concepts including case ID, activity, timestamp structures, and event log formats (XES or equivalent).
Strong data profiling and data quality assessment skills.
Ability to work iteratively in a fast-paced environment where requirements evolve based on model outputs.

Nice To Haves

Hands-on experience with IBM Process Mining (IBM Automated Business Process Discovery / IBM Process Mining platform) or similar tools (Celonis, UiPath Process Mining, Minit).
Experience with task mining platforms (e.g., UiPath Task Mining, Microsoft Task Mining) and processing desktop event log data.
Familiarity with ETL orchestration tools such as Apache Airflow, Informatica, Talend, SSIS, or Azure Data Factory.
Experience with cloud data platforms (AWS, Azure, or GCP) and associated data services.
Knowledge of BPMN (Business Process Model and Notation) and process improvement frameworks (Lean, Six Sigma).
Experience in a government contracting or regulated industry environment.
Master's degree in a relevant technical discipline.

Responsibilities

Design, build, and maintain ETL pipelines to extract data from diverse enterprise sources including ERP systems, CRM platforms, relational databases (SQL Server, Oracle, PostgreSQL), flat files, and APIs.
Transform raw data into structured event logs and case tables conforming to IBM Process Mining ingestion requirements (XES, CSV, or direct connector formats).
Perform data profiling, cleansing, deduplication, and normalization to ensure high-quality inputs for process model development.
Manage iterative data pulls as process models are refined and additional data requirements are identified by analysts and stakeholders.
Load event log and transaction log data into IBM Process Mining and configure case, activity, and timestamp mappings.
Collaborate with process analysts to build, validate, and iterate on process models that accurately reflect real-world workflows.
Support root cause analysis, conformance checking, and performance analysis within IBM Process Mining.
Identify bottlenecks, deviations, and rework loops in process data and communicate findings to business stakeholders.
Ingest and process desktop activity/event logs generated from task mining tools, mapping UI interactions to higher-level process steps.
Correlate task mining data with system-level transaction logs to produce enriched, end-to-end process views.
Validate task mining event structures and resolve data quality issues prior to model ingestion.
Partner with IT, database administrators, and application owners to gain data access and understand source system schemas.
Document ETL pipelines, data dictionaries, transformation logic, and model configurations for repeatability and auditability.
Communicate data limitations, assumptions, and model constraints clearly to non-technical stakeholders.
Support process improvement initiatives by providing data-driven insights derived from process model outputs.