Senior Data Scientist

Skyward IT Solutions•Maryland, MD

18d•Remote

About The Position

We are Skyward, a people-centered business focused on human advancement through information technology. We are seeking a Senior Data Scientist who is excited by the challenge of working with complex, disparate federal and private datasets. The ideal candidate understands the importance of thorough data analysis before model selection and can effectively communicate technical concepts to non-technical stakeholders. This role involves leading end-to-end data science experiments, including data readiness assessments, clustering, topological risk modeling, unstructured data enrichment, and entity resolution within a government-controlled environment. We value rigor, reproducibility, and a collaborative approach to modernizing government services.

Requirements

An active Secret clearance at time of hire.
7+ years of applied data science experience.
At least 2 years of experience with graph analytics or network analysis as a primary tool.
Strong production-grade Python skills: pandas, NumPy, scikit-learn, networkx (or graph-tool / igraph).
Experience with at least one GNN library such as PyTorch Geometric or DGL.
Real-world experience with probabilistic record linkage / entity resolution (e.g., Senzing, dedupe, FEBRL, Magellan, or a homegrown Fellegi-Sunter implementation).
Comfort working without labels (anomaly detection, positive-unlabeled learning, isolation forests, autoencoders).
Proficiency in evaluating models without clean ground truth.
Interpretability discipline: SHAP, feature importance, partial dependence plots, and the wisdom to pick simpler models when appropriate.
LLM application experience beyond prompt-and-pray, including entity and relationship extraction on real text with evaluation of extraction quality.
Statistical maturity: understanding of power analysis, confidence intervals, and the dangers of p-hacking.
Comfort presenting technical findings to non-technical operational stakeholders without losing nuance.
Reproducibility hygiene: ability to ship code that can be rerun by others, including version control, parameterized pipelines, deterministic seeds, pinned dependencies, and functional READMEs.

Nice To Haves

Published research, open-source contributions, or conference talks in entity resolution, graph ML, or applied causal inference.
Knowledge of commercial data sources like LexisNexis, Transunion, Babel Street, etc.
A track record of presenting null results to federal subject matter experts without flinching.
A reputation among teammates for finding pipeline bugs before they impact deliverables.

Responsibilities

Lead end-to-end data science experiments, from data readiness assessment through clustering and topological risk modeling, into unstructured-data enrichment and entity resolution.
Run exploratory data analyses (EDAs) on government-furnished data inside a government-controlled environment: profile completeness, find schema mismatches, flag gaps, and document data limitations.
Apply graph analytics, including Leiden community detection, centrality measures, motif analysis, temporal cluster detection, and link prediction, explaining each in plain English.
Train interpretable classifiers (logistic regression, gradient boosted trees) and Graph Neural Networks (GraphSAGE, GAT), and utilize unsupervised anomaly detection when labels are scarce.
Run probabilistic entity resolution across biographic, behavioral, and biometric features using tools such as Senzing, handling name transliteration, DOB variation, and fuzzy address matching.
Apply LLM-based Named Entity Recognition and relationship extraction to unstructured field text and quantify the impact on the graph.
Wrangle messy data and recommend supplemental, de-identified data sources to enrich analysis, documenting the case for each recommendation for customer review.
Document all work thoroughly to ensure customer rerun capability and reproducibility, which is a hard acceptance criterion.
Maintain rigor in analysis, including confidence intervals on all findings, documenting null findings with care, and avoiding dashboard theater.

Benefits

Medical, dental, vision insurance (fully paid for employees)
15 days of paid leave
7 days of sick leave
2 days bereavement leave
11 paid Federal holidays
Up to 40 hours for jury duty
401K with 4% employer contribution (and no vesting period)
Up to 4 weeks of paid paternity and maternity leave
Company provided laptop
$5,000 per year for professional development
$600 per year for technical supplies and equipment
$2,000 referral bonus
Life and disability insurance
HSA and FSA
Legal Shield and ID Shield
Voluntary Benefits
Opportunity to work in a collaborative, motivated team focused on modernizing government services with cutting-edge technology and innovative solutions.
Flexible working hours
Remote opportunities