About the Job: The ideal candidate will have a total of 12+ years of IT experience with extensive expertise in Python and leading AI/ML libraries (e.g., TensorFlow, PyTorch, Scikit-learn). Proficiency in open-source optimization (e.g., Pyomo, OR-Tools) is required to handle complex scheduling, routing, and resource allocation tasks. Data engineering experience—including Apache Spark, Hadoop, and Kafka—is crucial for building and managing data lakes that store both structured and unstructured data, supporting real-time data processing and analytics. The candidate should also have experience deploying AI solutions in both on-premises (Docker, Kubernetes) and cloud environments (AWS, GCP), with a strong understanding of DevOps practices (CI/CD, Git), security, and performance optimization. Familiarity with LLM and NLP frameworks such as SpaCy and NLTK is critical for developing Generative AI, chatbots, and automated customer service systems. Overall, expertise in a broad range of data engineering and AI technologies is essential for driving innovation and optimizing planning processes within the logistics industry, particularly in port and terminal operations.
Responsibilities: 1. Develop multi-agent AI frameworks geared toward container terminal operations and large-scale logistics optimization. 2. Design and implement end-to-end ML pipelines, including data ingestion, feature engineering, and real-time model deployment. 3. Optimize machine learning and deep learning algorithms for scheduling, resource allocation, and route planning in port environments. 4. Research and evaluate emerging AI techniques (e.g., generative models) to identify potential improvements in logistics workflows. 5. Collaborate with cross-functional teams to integrate AI solutions seamlessly into existing operational and IT infrastructures. 6. Build and maintain robust data pipelines (data lakes, streaming frameworks) using Spark, Hadoop, and Kafka for large-scale data handling. 7. Deploy AI solutions on both cloud platforms (AWS, GCP) and on-premises infrastructures, ensuring reliability, security, and compliance in high-volume environments. 8. Implement and fine-tune optimization models and solvers (OR TOOLS, COIN OR, SCIP, etc.) for complex port planning and container yard operations. 9. Conduct in-depth research and prototyping in reinforcement learning, agent-based modeling, and specialized ML techniques. 10. Apply reverse engineering methods to debug, interpret, and enhance existing ML models for continuous performance gains. 11. Monitor and report key metrics (KPIs, ROI) to assess the effectiveness of AI-driven solutions in real-world operations. 12. Integrate NLP and LLMs for customer service, documentation automation, and large-scale text analysis in logistics. 13. Collaborate on system integrations to ensure end-to-end functionality of AI modules across port operations. 14. Enable real-time intelligence for vessel scheduling, yard operations, and gate control using streaming data and on-the-fly analytics. 15. Maintain comprehensive domain knowledge of port and terminal terminologies to align AI solutions with operational realities. 16. Contribute technical insights to the organization’s digital transformation roadmap, supporting strategic AI initiatives. 17. Align AI R&D initiatives with the organization’s strategic vision, monitoring long-term impacts of AI-driven innovations, and influencing the overall digital transformation roadmap in the port and shipping sector.
