Requirements
What You'll Do:
• Work directly on a live client project developing time -series models geo science data
• Design, develop, and train time -series models to identify patterns, trends, and anomalies in continuous data streams
• Conduct model validation, back testing, and performance evaluation using appropriate time -series metrics
• Design and implement end -to -end MLOps pipelines for automated model training, versioning, deployment, and monitoring
• Deploy production -grade models using Docker, Kubernetes, and cloud ML services, ensuring scalability and reliability
• Implement monitoring and alerting mechanisms for model drift, data drift, and anomaly detection performance
• Optimize model performance for latency and real -time inference requirements
• Collaborate with the Technical Architect on infrastructure design, scalability planning, and cost optimization
• Document system architecture, model assumptions, experiments, and production workflows
Requirements:
• MTech / MSc in Machine Learning, Data Engineering, AI, or related field (current student or recent graduate)
• Strong Python skills and experience with ML frameworks (scikit -learn, PyTorch, or TensorFlow)
• Academic project experience with time -series data or ML pipelines
• Familiarity with MLOps concepts (model versioning, CI/CD, containerization)
• Bonus: Experience with time -series database or streaming data tools
What You'll Learn:
• Production -grade MLOps delivery for offshore wind sector
• Time -series forecasting at scale with real client data
• Cloud ML infrastructure architecture and deployment
• Agile delivery methodology for enterprise AI projects