Transportation Data Scientist (Mid-Level)

Leidos•McLean, VA
•$87,100 - $157,450•Hybrid

About The Position

Leidos seeks a mid-level Transportation Data Scientist to support FHWA-funded projects at the intersection of AI, data science, and transportation. The role is based at the FHWA Saxton Transportation Operations Laboratory (STOL), a USDOT research lab focused on improving transportation operations, safety, mobility, and environmental impacts. Projects may include vehicle-load classification using weigh-in-motion data and imagery, crash prediction for traffic management centers, and data ecosystems for trustworthy AI. The position involves building, deploying, and evaluating AI/ML models, including generative AI and LLM-based solutions, and taking models from raw data through deployment. Work also includes literature and data reviews, testing new methods, contributing to technical reports, and collaborating with stakeholders and cross-functional teams. Transportation experience is beneficial but not required. The role is based at a customer site in McLean, Virginia, with a current hybrid plan of four days onsite, and requires travel of up to 20%. Candidates must have lived in the United States for the three most recent consecutive years, be eligible to obtain and maintain a Public Trust clearance, and be legally authorized to work in the United States.

Requirements

  • Bachelor’s degree in computer science, data science, artificial intelligence, transportation engineering, or a related field, plus at least 4 years of relevant professional experience; or a master’s degree in one of these fields plus at least 2 years of relevant professional experience.
  • Relevant professional experience must be non-academic, hands-on work in data science or AI/ML; graduate research and coursework do not count toward the minimum.
  • Hands-on experience in at least two of these areas: data preparation and ETL for imperfect multi-source or multimodal data; model deployment beyond a notebook and familiarity with MLOps; or personally building generative AI solutions using LLMs or other generative models.
  • Strong Python skills and working knowledge of common machine learning and data libraries such as PyTorch or TensorFlow, Scikit-learn, Pandas, and NumPy.
  • Solid understanding of model evaluation, including measures such as precision, recall, F1, and AUC, and the ability to explain model performance, limitations, and troubleshooting.
  • Clear communication skills, including technical writing and presenting AI concepts to non-technical audiences.
  • Ability to work in a fast-paced, research-oriented environment and travel up to 20% for stakeholder meetings, site visits, or conference support.
  • Ability to obtain and maintain a Public Trust clearance; eligibility requires three years of immediate residency in the United States.
  • Legal authorization to work in the United States.

Nice To Haves

  • Ph.D. in a related field.
  • Experience working with state DOTs or federal transportation agencies, such as FHWA or USDOT, on AI initiatives, including prototyping AI applications in ITS.
  • Computer vision or deep learning experience, especially with imagery or video.
  • Familiarity with transportation data sources such as HSIS, SHRP2, and NGSIM, and standards such as SAE J2735 for V2X.
  • Experience with synthetic data generation, including GANs, or physics-informed machine learning.
  • Knowledge of federal AI governance, risk management, and equity considerations in transportation.
  • Experience leading AI tasks in multi-agency initiatives or contributing to communities of practice.
  • Publications or presentations at AI or transportation conferences, such as TRB or ITS America.

Responsibilities

  • Build ETL pipelines to clean, normalize, enrich, and fuse data from multiple sources, and address data quality issues such as inconsistency, sparsity, and bias.
  • Design, develop, and deploy AI/ML models for transportation applications, including generative AI and LLM-based solutions.
  • Package and deploy models into working environments and support MLOps practices such as versioning, monitoring, and retraining.
  • Evaluate model performance under varied conditions, including differing data quality, and recommend improvements to robustness, scalability, and trustworthiness.
  • Conduct targeted literature and data reviews on AI methods, datasets, and technologies relevant to freight analytics, traffic safety, and operations.
  • Support stakeholder outreach, including peer exchanges, workshops, and technical briefings with state DOTs, MPOs, enforcement agencies, and vendors.
  • Collaborate with cross-functional teams to align projects with USDOT goals, risk management, quality assurance, and federal standards.
  • Contribute to monthly progress reports, risk mitigation, and iterative model refinement based on federal feedback.
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service