Data Scientist

The Intersect Group; Greenville (SC); Sur place; USD 90 000 - 130 000; Plein temps

Résumé du poste

The Intersect Group in Greenville, SC is seeking a Data Scientist II to help develop, deploy, and operationalize machine-learning solutions within a production-scale ecosystem. You will balance hands-on modeling with building scalable pipelines and collaborating with a seasoned team.

You’ll transform complex data into predictive features, validate models, monitor drift, and contribute to AI initiatives across the business while communicating findings to stakeholders.

Qualifications

• Master's degree in a quantitative field.
• Strong foundations in statistics and ML.
• Proficient coding in R and/or Python.
• Experience with SQL and data manipulation.
• Ability to explain complex methods to non-technical partners.

Responsabilités

• Develop predictive models using statistical methods and ML.
• Create scalable model-building pipelines.
• Perform feature engineering from domain data.
• Validate models and monitor production performance.
• Collaborate with data science and IT teams to deploy models.
• Explore generative AI initiatives as needed.
• Communicate results to stakeholders and leadership.

Connaissances

Statistics & ML foundations

Feature engineering

R & Python coding

SQL

Communication

Collaboration

Formation

Master's degree in Applied Mathematics / Statistics / CS

Outils

R

Python

SQL

Description du poste

We are seeking a Data Scientist II to join a Data Science team and help develop, improve, and operationalize machine-learning and AI solutions. This role combines hands-on predictive modeling with the development of scalable model-building pipelines and support for a large production model ecosystem.

We are looking for someone who enjoys solving challenging quantitative problems and brings a strong foundation in mathematics and statistics, good coding skills, and a naturally curious and creative mind. The successful candidate should be eager to learn from experienced data scientists while contributing ideas, models, and tools that make the team more effective at scale.

The position offers ample opportunity to learn from a seasoned, friendly, and collaborative Data Science team with a long track record of publishing highly cited original research in prominent mathematical and statistical journals. This environment provides an excellent foundation for rapid professional growth in data science while working on consequential, real-world business problems.

Daily Responsibilities

• Independently develop high-quality predictive models using statistical methods, machine-learning algorithms, strong quantitative reasoning, and creative problem-solving.
• Generate powerful and reliable predictive features using domain knowledge, data exploration, and advanced feature-engineering techniques.
• Use appropriate model diagnostics to understand model behavior, identify weaknesses, and guide model improvements.
• Use rigorous validation and data-quality assessments to ensure models are statistically sound, production-ready, and stable on new data over time.
• Continuously improve models by evaluating alternative algorithms, model structures, predictors, and data sources.
• Contribute to applied generative AI initiatives as business needs arise, which may include chatbots and conversational AI components for AI phone agents.
• Build monitoring and alerting solutions for data quality, model drift, stability, and predictive performance.
• Use R and/or Python to manipulate data, implement algorithms, and automate ETL, feature generation, model fitting, validation, deployment, periodic retraining and refitting, monitoring, and dashboarding.
• Use approved generative AI tools, such as GitHub Copilot in Visual Studio Code, to develop high-quality code efficiently.
• Take ownership of modeling projects and initiatives, independently driving work from problem definition and data preparation through model development, implementation, and communication of results.
• Help maintain and improve an ecosystem of approximately 150 production models through model development, automated scoring, performance monitoring, diagnostics, retraining, refitting, and remediation, working with IT to deploy models and monitoring tools into production.
• Explore new statistical, machine-learning, and data-science techniques applicable to predictive modeling and quantitative analysis, and incorporate promising methods into the team’s modeling best practices.
• Explore emerging AI technologies, including large language models, embeddings, natural language processing, and AI agents, and evaluate their application to relevant business problems.
• Communicate methodology, findings, model limitations, and recommendations clearly to stakeholders, and present results to senior and executive management.

Requirements

• Master's degree in Applied Mathematics, Statistics, Computer Science, Engineering, or another quantitative field.
• Strong foundation in mathematics, statistics, quantitative problem solving, and machine learning.
• Strong programming and algorithmic problem-solving skills in R and/or Python, with the ability to write efficient, maintainable analytical code.
• Natural curiosity, creativity, and an eagerness to learn from experienced colleagues and master unfamiliar methods, tools, and business domains quickly.
• Strong communication and collaboration skills, including the ability to explain technical work to nontechnical partners.
• Two to four years of professional experience in data science, machine learning, data engineering, or a closely related field.
• Experience working with structured data and building predictive models from complex, real-world datasets is a plus.
• Working knowledge of SQL; experience with big-data and cloud platforms.