Senior Analyst, Data Science

LPL Financial•Charlotte, NC

About The Position

We are seeking a curious and analytically rigorous Senior Analyst, Data Science to design and build models, analyses, and decision-support tools that drive transformation across the firm's home-office functions — Service, Operations, Supervision, Compliance, Legal, and Risk. This role sits on a small, high-leverage data science team within our Data Analytics & Reporting organization, chartered to deliver trusted, AI-enabled insights that drive measurable business outcomes for a Fortune 500 broker-dealer. You'll closely collaborate with the team and key business partners to frame analytical problems, design and execute analyses, and translate results into actionable recommendations. This is a high-impact, hands-on role for someone who wants to apply classical data science methods — machine learning, statistics, anomaly detection, and causal inference — to consequential problems in a regulated environment, where the quality of a model depends as much on understanding the business and regulatory context as it does on the math.

Requirements

3+ years of experience in data science, quantitative analysis, or applied research role in a business setting.
Bachelor's degree in Statistics, Mathematics, Computer Science, Economics, Data Science, or a related quantitative field required
Experience with Python for data manipulation, statistical analysis, and machine learning that goes beyond Jupyter notebooks; strives for clean, Git version-controlled code.
Experience working with large-scale data in SQL & Snowflake; comfortable building and maintaining clean, reproducible data pipelines as needed to support modeling and analysis work.
Solid grounding in statistics, probability, and machine learning fundamentals.
Hands-on experience with causal inference methods and experimental design.
Exposure to anomaly detection techniques applied to surveillance, fraud, or risk problems.
Data visualization skills and the ability to communicate findings clearly to non-technical stakeholders; note this role will not be focused on developing dashboards.

Nice To Haves

Direct experience as a data scientist or quantitative analyst inside a FINRA-registered broker-dealer, with hands-on work supporting one or more home-office functions such as Service, Operations, Supervision, Compliance, Legal, or Risk.
Working knowledge of the regulatory framework that governs broker-dealer activity (SEC, FINRA, state securities regulators) and an appreciation for how that framework may influence the design of data science solutions that ensure our stakeholders can continue to meet their regulatory obligations
Active FINRA registration (e.g., Series 7, Series 24, Series 99) is unusual for a data candidate and would be considered a meaningful differentiator.

Responsibilities

Design and execute end-to-end analyses that surface meaningful business insights, from data extraction and cleaning through modeling and interpretation.
Apply statistical methods — including hypothesis testing, regression, and causal inference — to answer business questions with the rigor and clarity expected in a regulated environment.
Translate complex analytical outputs into clear narratives and visualizations for business stakeholders and senior leadership.
Build, validate, and deploy supervised and unsupervised machine learning models supporting use cases such as risk tiering, surveillance and alert prioritization, anomaly detection, segmentation, and workload/cost-to-serve modeling.
Evaluate model performance using appropriate metrics and clearly communicate trade-offs, assumptions, and limitations to both technical and non-technical audiences.
Stay current on advances in applied ML and bring emerging methods to bear on relevant business problems.
Design and analyze A/B tests and observational studies to identify causal relationships and measure the impact of business initiatives.
Apply quasi-experimental methods when randomized experiments are not feasible.
Partner with business teams to build a culture of evidence-based decision-making.
Work closely with data engineers, product managers, business stakeholders, and subject matter experts to access, understand, and leverage data assets across the enterprise.
Document analytical workflows, assumptions, code, and findings to ensure reproducibility, knowledge sharing, and audit readiness.
Contribute to building a scalable data science practice by identifying opportunities to improve tools, processes, and methodologies.