Data Scientist I

Odyssey•Charlotte, NC

3d•Hybrid

About The Position

Odyssey Logistics is a global logistics and supply chain partner helping businesses optimize performance through fully integrated, end-to-end solutions. We connect transportation, technology, and expertise across a broad network of services including 3PL and 4PL managed services, multimodal and intermodal transport, warehousing, trucking, Jones Act Ocean, and customs brokerage, ensuring goods move reliably, efficiently, and intelligently around the world. Today, Odyssey supports more than 6,000 customers globally, delivering scalable, data driven solutions across complex supply chains. What started with a single client has grown into a dynamic, evolving organization focused on performance, precision, and long-term partnership. Our work is complex, fast moving, and highly collaborative. Success here requires people who think strategically, operate with urgency, and navigate across functions to solve real business challenges. We value individuals who take ownership, challenge the status quo, and turn insight into action. Our culture is grounded in five core values: Win Together, Innovate Boldly, Drive Results, Customer Centric, and Guide with Care. These are not just principles; they shape how we make decisions, partner with customers, and show up for each other. All applicants must be currently authorized to work in the United States. No relocation allowance will be considered unless specifically addressed. Seeking a highly analytical, innovative, and research-driven Data Scientist to lead the research, design, development, and implementation of advanced artificial intelligence, machine learning, optimization, and geospatial analytics solutions. This role drives end-to-end applied research initiatives, translating cutting-edge modeling approaches into scalable, production-ready systems that solve complex business challenges in logistics and supply chain. The ideal candidate combines deep technical expertise with strong business acumen to provide technical leadership, mentor junior team members, and shape AI-enabled decision-making.

Requirements

Degree in Data Science, Computer Science, Engineering, Statistics, Artificial Intelligence, or a related quantitative field (PhD preferred).
3+ years of experience applying data science, advanced AI, predictive/prescriptive analytics, and intelligent systems development in enterprise, operational, or supply chain domains.
Strong background in deep learning architectures, including experience with neural network-based modeling approaches for forecasting, classification, sequence modeling, and recommendation systems.
Experience conducting applied research, experimentation, and model benchmarking, including algorithm comparison, performance evaluation, error analysis, and iterative model improvement.
Strong proficiency in building advanced machine learning and statistical models using Python, SQL, and modern frameworks (e.g., PyTorch, TensorFlow, Scikit-learn).
Experience with geospatial analytics and spatial data science methods, including working with tools such as PostGIS, QGIS, ArcGIS, or GeoPandas.
Hands-on experience with scalable experimentation, feature engineering, and data preparation using large-scale datasets in modern cloud-based environments (e.g., Databricks, AWS, Azure, GCP, MLflow).
Demonstrated experience with Generative AI, large language models (LLMs), intelligent automation, and optimization methods (e.g., simulation, forecasting, decision science).
Proficient in querying, manipulating, and wrangling complex datasets to support pipeline development.
Knowledge of business intelligence tools (e.g., Sigma Computing, Power BI, Tableau) to support visual storytelling, continuous performance monitoring, and business adoption.
Deep understanding of model monitoring, explainability, reproducibility, data governance, and responsible AI practices.
Strong analytical and communication skills, with a demonstrated ability to convey advanced technical research and methodology to both technical and non-technical stakeholders
Proven ability to lead technical initiatives, mentor team members, and work collaboratively in cross-functional teams (research publications or peer-reviewed work is a plus).

Nice To Haves

PhD preferred.
research publications or peer-reviewed work is a plus.

Responsibilities

Lead applied research, design, and implementation of advanced AI, machine learning, and spatial-analytics solutions—including Generative AI, predictive modeling, and intelligent automation—to solve complex supply-chain challenges.
Drive end-to-end applied research cycles: problem framing, data exploration, feature engineering, rigorous experimentation, validation, and deployment support.
Lead rigorous analytical experimentation to evaluate algorithms, compare methodologies, analyze errors, and identify the most effective approaches for operational use cases.
Leverage geospatial intelligence and spatial-temporal analysis to support advanced modeling in routing, territory design, network optimization, and service performance improvement.
Develop and deploy intelligent AI-powered systems to forecast demand, improve pricing strategies, optimize asset utilization, and enhance overall business efficiency.
Establish robust model evaluation, monitoring, and explainability frameworks to ensure algorithms remain accurate, reliable, and responsive to dynamic logistics environments.
Translate complex technical research and advanced analyses into clear, actionable business recommendations through dashboards, reports, and stakeholder communication.
Provide technical leadership in the architecture of analytical products, collaborating with engineering teams to design internal AI applications, automation tools, and knowledge-based systems.
Proactively stay current with advancements in artificial intelligence, deep learning, and optimization, applying state-of-the-art research methods to drive operational excellence.
Document methodologies, model architectures, assumptions, and implementation processes to support reproducibility, transparency, and long-term scalability.
Provide technical mentorship to junior data scientists, support the hiring and onboarding processes, and contribute to a culture of innovation through team knowledge-sharing and peer reviews.