Research Intern - GHAI-3

Job Description Research Intern - GHAI-3 Job Location: Santa Clara, California Location Flexibility: Multiple Locations in Country Req Id: 8047 Posting Start Date: 5/8/26 At Fujitsu, we are driven by our purpose to make the world more sustainable by building trust in society through innovation. We have been a pioneer in technology and innovation for over 80 years, and we are committed to using our expertise to help businesses and organizations transform for the digital age. We believe that digital transformation is essential to creating a more sustainable future. That's why we are working with our customers to develop solutions that can help them reduce their environmental impact, improve their efficiency, and create a more equitable society. We are committed to contributing to the United Nations Sustainable Development Goals (SDGs). These goals are a blueprint for a better future for all, and we believe that technology can play a vital role in achieving them. If you share our passion for making a meaningful impact on the world, we invite you to join our global family of 130,000 employees spanning more than 50 countries. We are a diverse workforce, and we offer a wide range of opportunities for you to grow and develop your career. Together, we can create a more sustainable future for all. Research Intern at Fujitsu Research of America Location: Santa Clara, CA The Space Data Frontier Research Center at Fujitsu focuses on combining research across multiple technical fields to address large-scale societal and industrial challenges. These challenges require new approaches that integrate artificial intelligence, sensing, modeling, optimization, and domain knowledge. Our goal is to develop evidence-based scientific tools that support decision-making, improve operational efficiency, and accelerate innovation across industries. We are seeking exceptional research interns to join our Space Data Frontier Research Center Lab in Silicon Valley to work on next-generation maritime intelligence and port operations optimization. This project aims to develop an integrated decision-support framework that combines multi-source sensor fusion with port operations visibility and what-if planning. The framework will use heterogeneous data sources, including SAR imagery, optical imagery, AIS, RF signals, and port-area imagery, to track vessels, estimate operational states, diagnose congestion, and support improved port planning and control. The internship duration is 3 months. Job responsibilities Building on an existing AIS-based congestion-modeling pipeline for the San Pedro Bay port complex (Ports of Long Beach and Los Angeles), the intern will deliver (a) machine-learning models that forecast vessel Estimated Time of Arrival (ETA) at the berth, and (b) an interactive operational dashboard that presents predicted Congestion Index (CI), ETAs, port-state KPIs, short-horizon congestion forecasts, and weather-event annotations. The intern joins an active project with an existing data pipeline, a defined CI, and an early XGBoost / Ridge baseline. Machine Learning Develop and benchmark gradient-boosted (XGBoost, LightGBM) and regularized linear (Ridge, Lasso) forecasting models for ETA. Use TimeSeriesSplit cross-validation and Bayesian hyperparameter tuning (Optuna) to ensure causal, leak-free evaluation; report skill scores against persistence and naive baselines. Operational Dashboard Build an interactive dashboard in Streamlit (or Plotly Dash) presenting predicted ETAs for inbound vessels, current port-state KPIs (queue length, berth occupancy, CI), 1h / 3h / 6h congestion forecasts with uncertainty bands, and weather-event overlays. Implement geospatial visualizations (vessel positions, terminals, anchorage zones) using Folium, Plotly Mapbox, deck.gl, or equivalent, with drill-down filtering. Include a model-performance panel (rolling MAE / RMSE, predicted-vs-actual, drift indicators) for stakeholder trust. Package the dashboard as a reproducible repository with documentation, configuration, and a containerized deployment path (Docker or Streamlit Community Cloud). Requirements Currently enrolled in a master's or PhD program in computer science, data science, civil / transportation engineering, operations research, or a closely related field. Strong Python with pandas, NumPy, scikit-learn, Matplotlib / Seaborn, and at least one of XGBoost / LightGBM. Solid foundation in supervised regression with time-series concepts (lag features, temporal splits, target leakage). Demonstrated experience building interactive dashboards in Streamlit, Plotly Dash, or equivalent — please share a public exam