Transportation Data Scientist

Description

Are you interested in shaping the future of transportation? Consider joining the Leidos team operating FHWA's Saxton Transportation Operations Laboratory (STOL), a USDOT research lab focused on the improvement of transportation operations, safety, mobility, and environmental impacts. STOL provides a variety of services to support the advancement and adoption of emerging technologies, including automation and communication in vehicles and on the roadside.

This role requires full-time on-site work at the customer site in McLean, VA
.

Learn about STOL here: (Use the "Apply for this Job" box below)./STOL

All applicants must be legally authorized to work in the United States with proof of legal status and be eligible for a Public Trust Clearance which includes three consecutive years in the United States within the last five years.

Leidos is seeking a highly skilled Transportation Data Scientist to support FHWA-funded projects at the intersection of AI, data science, and transportation. This role will focus on developing and deploying AI/ML models for applications such as vehicle load classification using weigh-in-motion (WIM) data and imagery, crash prediction in traffic management centers (TMCs), and creating data ecosystems for trustworthy AI. The ideal candidate will have hands-on experience in AI model development, data integration, and stakeholder engagement, with a passion for identifying new opportunities to apply AI in state-level transportation initiatives.

This position offers the chance to drive innovation in a dynamic, federally supported research environment.

• Conduct data and literature reviews, including targeted searches for AI methods, datasets, and technologies relevant to freight analytics, traffic safety, and operations (e.g., sensor fusion, computer vision, and multimodal AI).
• Prepare and integrate datasets for AI use cases, including cleaning, normalizing, enriching, and fusing multi-source data (e.g., traffic logs, imagery, weather, and permitting records) while addressing quality issues like inconsistency, sparsity, and bias.
• Lead the design, development, and deployment of AI/ML models for transportation applications, including classifying oversized/overweight (OS/OW) vehicles using WIM data and imagery, crash prediction in TMCs, and generating synthetic data for model training.
• Evaluate AI model performance under diverse conditions, such as varying data quality levels, and provide recommendations for improving model robustness, scalability, and trustworthiness in real-world transportation environments.
• Support stakeholder outreach and engagement, including organizing peer exchanges, workshops, and technical briefings with state DOTs, MPOs, enforcement agencies, and vendors to gather insights on AI applications in WIM systems, permitting integration, and crash prediction.
• Identify and pursue new opportunities with state DOTs for AI initiatives, including contributions to developing roadmaps, proposals, and implementation strategies for AI in ITS, such as anomaly detection, traffic optimization, and safety analytics.
• Collaborate with cross-functional teams to ensure project alignment with FHWA goals, including risk management, quality assurance, and compliance with federal standards.
• Provide technical leadership in monthly progress reporting, risk mitigation, and iterative model refinement based on federal feedback.

• Bachelor2s degree in computer science, Data Science, Artificial Intelligence, Electrical Engineering, Transportation Engineering, or a related field;
  Master2s or Ph.D. preferred.
• 5+ years of professional experience in data science and AI/ML, with demonstrated expertise in machine learning frameworks (e.g., Tensor Flow, PyTorch, Scikit-learn), data processing tools (e.g., Pandas, Num Py), and AI techniques (e.g., deep learning, generative AI like GANs, computer vision).
• Experience collaborating with state and local DOTs and developing new customers / business development experience.
• Minimum of 2+ years of relevant non-academic experience.

Additional qualifications include proven experience in data preparation and integration, ETL, handling multimodal data (e.g., imagery, sensor data, time-series), and addressing data quality challenges in real-world applications; strong analytical skills with experience in model evaluation metrics (e.g., AUC, accuracy, scalability); excellent communication and collaboration skills for stakeholder engagement; ability to work in a fast-paced, research-oriented environment with travel up to 20% for stakeholder meetings and site visits;

ability to obtain and maintain a Public Trust clearance; and eligibility to work in the United States without company sponsorship.

Prior experience working with state DOTs or federal transportation agencies (e.g., FHWA, USDOT) on AI initiatives, including developing AI roadmaps,…