The Artificial Intelligence in Transportation (AIT) Lab at Texas State University is offering research assistant opportunities for motivated PhD and MS students, as well as outstanding undergraduates. The lab focuses on leveraging artificial intelligence and machine learning to address safety-critical transportation research challenges. Projects involve working with large-scale crash data, infrastructure data, multimodal mobility datasets, and developing AI-driven decision support tools for transportation systems.

Core responsibilities include developing and benchmarking models for crash severity, driver behavior, and infrastructure risk, building end-to-end machine learning pipelines (from preprocessing to deployment), implementing explainable and trustworthy AI methods (such as counterfactuals, causal inference, and mechanistic AI), contributing to journals and conferences in transportation, AI, and data science, maintaining reproducible research-quality codebases for long-term use and open-source release, and collaborating with interdisciplinary teams across engineering, AI, and policy.

Applicants should have strong foundations in artificial intelligence and software engineering, proficiency in Python for deep learning, experience with PyTorch and/or TensorFlow, knowledge of statistical learning, validation, and uncertainty analysis, and experience with large datasets (SQL, Pandas, NumPy) and spatial AI. Strong software practices (Git, documentation, experiment tracking) are required. Preferred qualifications include prior AI or research experience in computer science, statistics, transportation, or related fields, evidence of strong analytics (publications, preprints, competitions, open source), and for PhD applicants, independent methodological research capability, 2 Q1 publications, and 500+ GitHub stars. MS/UG applicants should have excellent coursework, a research mindset, and 1000+ GitHub stars.

The research assistantship is renewable for 12–24 months based on performance. The specific stipend amount and tuition coverage are not mentioned. The start date is flexible. Interested candidates should send a brief introduction, CV, and links to GitHub, Google Scholar, or prior work (if available) to Dr. Subasish Das at [email protected].