Senior Data Scientist

Seneca Holdings; Buffalo (NY); On-site; USD 120,000 - 180,000; Full time

Job summary

Three Sisters Federal is seeking a Senior Data Scientist to support a Department of Veterans Affairs program focused on workforce learning, education, and development across the VA health system. The role blends data engineering with analytics, using SQL Server and Power BI to deliver actionable insights.

You will modernize ETL pipelines, implement Python-based data cleansing, and extend visualization with Python visuals in Power BI, while coordinating with stakeholders and maintaining strong

Qualifications

• 5+ years of experience in data science, data engineering, or advanced analytics.
• Advanced SQL and hands-on experience with on-premises Microsoft SQL Server, including performance tuning.
• Strong Python for data work and visualization, including programmatic charting and database connectivity.
• Demonstrated Power BI development, including DAX and semantic model design.
• Experience building and maintaining ETL processes (SSIS or comparable).
• Experience with ML, regression, forecasting, and time series.
• Ability to present findings to non-technical stakeholders.
• Must be a U.S. citizen, as required by the customer for this position.

Responsibilities

• Data Engineering: Build and maintain a SQL Server data warehouse with ETL from multiple applications and SharePoint.
• Data Engineering: Replace cursor-based data cleansing with Python-based processing.
• Data Engineering: Document ETL workflows and dependencies to reduce tech debt.
• Data Engineering: Design external orchestration and credential management for scheduled jobs.
• Analytics: Conduct statistical analysis, regression, and predictive modeling.
• Analytics: Apply machine learning and text analytics where value is added.
• BI: Design and maintain Power BI semantic models, reports, and dashboards.
• BI: Respond to rapid ad-hoc data calls from leadership and inquiries.
• Documentation: Produce technical docs and process maps.
• Stakeholders: Translate questions into measurable analyses and present findings.

Skills

Advanced SQL

Python

Power BI

Data Modeling

Statistical Analysis

Machine Learning

Data Visualization

Documentation

Education

Bachelor's degree in a quantitative or technical field

Tools

SQL Server

SSIS

Python

Airflow

Azure Data Factory

Microsoft Fabric

Job description

Three Sisters Federal is part of the Seneca Nation Group (SNG) portfolio of companies. SNGis Seneca Holdings' federal government contracting business that meets mission-critical needs of federal civilian, defense, and intelligence community customers. Our portfolio comprises multiple subsidiaries that participate in the Small Business Administration 8(a) program. To learn more about SNG, visitthe website and follow us onLinkedIn.

Our team of talented individuals is what makes us successful. To support our team, we provide a balanced mix of benefits and programs.Your total rewards package includes competitive pay, benefits, and perks, flexible work-life balance, professional development opportunities, and performance and recognition programs. We offer a comprehensive benefits package that includes medical, dental, vision, life, and disability, voluntary benefit programs (critical illness, hospital, and accident), health savings and flexible spending accounts, and retirement 401K plan. One of our fundamental principles is to offer competitive health and welfare benefits to our team members, providing coverage and care for you and your family. Full-time employees working at least 30 hours a week on a regular basis are eligible to participate in our benefits and paid leave programs. We pride ourselves on our collaborative work environment and culture, which embraces our mission of providing financial and non-financial benefits back to the members of the Seneca Nation.

Three Sisters Federal is seeking a Senior Data Scientist to support a Department of Veterans Affairs (VA) Veterans Health Administration customer responsible for workforce learning, education, and development across the largest integrated health system in the United States. The customer converts raw training and workforce data into reporting that leadership, program offices, and congressional inquiries rely on.

This is a hands‑on individual contributor role working on a small team. The work is roughly evenly split between data engineering (SQL Server ETL, pipeline modernization, data quality) and analytics delivery (Power BI semantic models, dashboards, statistical analysis, rapid‑turnaround data calls). The environment today is on‑premises SQL Server with Power BI; a meaningful part of this role is helping move it forward.

We are looking for someone who does excellent analytical work and can also design the environment that analytical work depends on. Decisions about tooling, infrastructure, and platform direction rest with the customer, so the value here is in arriving with options rather than assumptions: laying out approaches with their trade‑offs, cost and access implications, and migration paths, in enough detail that a decision can be made, and then implementing what is approved. Candidates who have thought through how to set up an analytics environment, and not only how to work inside one someone else built, will be a strong fit.

Beyond sustaining current reporting, our preferred candidate can expand this role by maturing the analytics platform and the engineering practices around it. That work may include automating data cleansing in Python at the point of arrival and retiring the cursor‑based cleansing routines that currently run inside SQL Server; standing up source control and dependency management so analytical code is reproducible across machines; extending visualization beyond native Power BI through programmatic charting delivered as Python visuals inside Power BI reports, with interactive and publication‑quality table output available outside the report canvas; and connecting to source systems through Python database connectors rather than manual extracts. While SSIS remains in place, but pipeline orchestration could move outside SQL Server, with options like Apache Airflow and Microsoft Fabric among the candidates under evaluation, and with credential management handled as a deliberate part of the design rather than an afterthought. The role could also maintain a technical backlog covering planned engineering work, nice‑to‑have improvements, and identified deficiencies affecting data security or data quality, so remediation and enhancement are sequenced deliberately rather than handled as each request arrives.

Responsibilities

Data Engineering and Pipeline Modernization

• Build and maintain a SQL Server data warehouse, including ETL processes sourcing from multiple enterprise applications and SharePoint.
• Replace cursor‑based data cleansing routines in SQL Server with Python‑based processing.
• Catalog and document existing ETL workflows and their interdependencies to reduce technical debt.
• Design pipeline orchestration outside of SQL Server, including credential and secrets management for scheduled jobs and data connections; evaluate candidate tools against the customer's constraints, present recommendations, and implement the approved approach.
• Establish source control and dependency management practices so analytical code runs reproducibly across machines and environments.
• Design a repeatable deployment process for ETL and analytics code, moving changes from development through test to production with peer review, versioned releases, and a rollback path, and document what tooling and access each option would require so the customer can decide what to stand up.

Analytics and Modeling

• Conduct statistical analysis, regression, and predictive modeling to answer organizational questions and support projections.
• Apply machine learning and text analytics methods where they demonstrably add value, including classification, forecasting, and segmentation, and make the ROI case before committing to an approach.
• Perform exploratory analysis on new and archival data sources to surface trends that conventional reporting misses.
• Design and implement data quality controls, including automated validation.
• Evaluate model performance and refine methods over time.
• Maintain a technical backlog of planned engineering work, nice‑to‑have improvements, and identified deficiencies affecting data security or data quality, and work with stakeholders to sequence remediation.

Business Intelligence and Reporting

• Design, build, and maintain Power BI semantic models, reports, and dashboards, including KPI and performance‑tracking products.
• Diagnose and resolve Power BI performance problems, including decomposing monolithic semantic models into separate, targeted models and updating downstream reports.
• Develop custom visualizations programmatically in Python, embedded as Python visuals in Power BI where native visuals fall short, and produce interactive or publication‑quality tabular output outside the Power BI canvas where the audience calls for it.
• Respond to rapid‑turnaround ad‑hoc data calls from senior leadership and external inquiries.
• Define measurements and KPIs, and build reporting standards and templates that make findings usable without rework.

Documentation and Stakeholder Support

• Produce and maintain technical documentation, system maps, and process flow diagrams.
• Work directly with program stakeholders to translate ambiguous questions into measurable analysis.
• Consult on data design for enterprise applications under development.
• Present findings and recommendations to non‑technical audiences.

Required Qualifications

• 5+ years of experience in data science, data engineering, or advanced analytics. Bachelor's degree in a quantitative or technical field preferred; equivalent professional experience accepted in lieu of a degree.
• Advanced SQL and hands‑on experience with on‑premises Microsoft SQL Server, including performance tuning.
• Strong Python for data work: dataframe‑based manipulation and numerical computing, programmatic charting, and querying SQL Server directly through a Python database connector.
• Demonstrated Power BI development experience, including DAX, Power Query, semantic model design, and performance optimization.
• Experience building and maintaining ETL processes (SSIS or comparable).
• Applied experience across a range of analytical methods: regression, classification, time series forecasting, clustering and segmentation, dimensionality reduction, and statistical inference including hypothesis testing and uncertainty quantification.
• Working knowledge of version control and Python environment/dependency management.
• Experience assessing an existing analytics environment and producing design options with trade‑offs, dependencies, and implementation paths for decision‑makers who control the tooling and infrastructure.
• Ability to document work clearly and communicate analytical findings to non‑technical stakeholders.
• Ability to obtain and maintain a VA background investigation and PIV credential.
• Must be a U.S. citizen, as required by the customer for this position.

Preferred Qualifications

• Experience with pipeline orchestration tools such as Apache Airflow, Azure Data Factory, or comparable.
• Exposure to Microsoft Fabric, Azure Synapse Analytics, or Azure Machine Learning, and a point of view on when migration is warranted.
• Experience implementing deployment pipelines or CI/CD for Power BI assets.
• Interactive visualization and publication‑quality tabular reporting beyond standard dashboard tooling.
• Tree‑based ensemble methods on tabular data.
• Time series methods: seasonal decomposition, and validation approaches appropriate to temporal data.
• Text analytics on unstructured sources: topic modeling, text classification, and entity extraction.
• Experiment tracking and model lifecycle practices.
• Experience collaborating with SharePoint and Power Platform developers on shared data models.
• Prior VA, VHA, or federal health IT experience.
• Microsoft certifications: Power BI Data Analyst Associate (PL‑300) or Azure Data Scientist Associate (DP‑100).

Equal Opportunity Statement:
Seneca Holdings provides equal employment opportunities to all employees and applicants without regard to race, color, religion, sex/gender, sexual orientation, national origin, age, disability, marital status, genetic information and/or predisposing genetic characteristics, victim of domestic violence status, veteran status, or other protected class status. This policy applies to all terms and conditions of employment, including, but not limited to, hiring, placement, promotion, termination, layoff, recall, transfer, leave of absence, compensation and training. The Company also prohibits retaliation against any employee who exercises his or her rights under applicable anti‑discrimination laws. Notwithstanding the foregoing, the Company does give hiring preference to Seneca or Native individuals. Veterans with expertise in these areas are highly encouraged to apply.