Ismail Arjdal

Responsibilities:

• Delivering High-Impact Data Models: Lead a team in developing machine learning models, focusing on analyzing sensor data from cars for predictive maintenance, customer profiling, anomaly detection, and time series forecasting.
• Enhance Time Series Forecasting Capabilities: Oversee data preprocessing, feature engineering, and the deployment of time series models. Use a mix of statistical models for detecting seasonality, XGBoost for improving accuracy, and deep learning approaches like LSTMs and TCNs to effectively manage and predict complex temporal patterns. Consistently measure and optimize model performance using RMSE (Root Mean Square Error) as a key metric.
• Building Reliable Data Pipelines: Design and implement robust ETL pipelines to integrate large datasets, ensuring data quality and consistency for modeling.
• Accelerating Scalable Model Deployment: Streamline MLOps processes using Kubeflow to automate workflows and enhance performance monitoring.
• Transforming Data into Insights: Create and manage the development of interactive Tableau dashboards and Streamlit applications for real-time data visualization.
• Collaborating with Stakeholders: Bridge the communication gap between technical and non-technical teams, ensuring that machine learning insights align with business strategies.

Achievements:

• Model Precision and Recall: Achieved 90% precision and recall on ML models, significantly enhancing decision-making and operational efficiency.
• Robust Pipeline Integration: Successfully integrated large datasets into reliable pipelines that powered predictive models for accurate forecasts.
• Reduction in Development Cycles: Achieved an 80% reduction in model development cycles, enabling efficient scaling of models in Google Cloud Platform (GCP).
• Real-Time Decision-Making: Enabled real-time views of trends and metrics, facilitating data-driven decisions across the team.
• Enhanced Team Capabilities: Developed and led a comprehensive ML and MLOps training program to enhance team skills and promote a culture of innovation.

Responsibilities:

• Meeting Analytical Requirements: Collaborated with team members and leaders to identify and address analytical needs, ensuring the collection and analysis of pertinent information for customer and project requirements.
• Developing Deep Learning Models: Engineered and deployed deep learning models using PyTorch, specifically for the detection of structural cracks in images from in-service reports.
• Automating Data Collection: Designed and implemented scripts to automate the collection and processing of training data, enhancing the efficiency of the model development workflow.
• Enhancing Operational Efficiency through Digitization: Developed and deployed Google App Scripts and APIs to automate data processing and integration into web applications, ensuring improved data accessibility and operational efficiency.

Achievements:

• Enhanced Predictive Maintenance: Successfully deployed deep learning models that improved predictive maintenance capabilities by accurately detecting structural cracks, thereby reducing the time and cost associated with manual inspections.
• Streamlined Model Development Workflow: Automation of data collection and processing significantly streamlined the model development process, enhancing data readiness and reducing time to deployment.

Responsibilities:

• Building Visualization Tools for Decision Support: Created data visualization tools that provided insights for key decisions, contributing to improved project outcomes and enabling data-driven decision-making.
• Automating Structural Analysis: Developed tools for automating spar repair analysis, using advanced engineering methods to ensure consistency and reduce manual workload.
• Collaborating with Cross-Functional Teams: Worked with multidisciplinary teams to address complex engineering challenges, facilitating a data-centric approach to design and analysis.

Responsibilities:

• Conducting Structural Analysis and Problem Solving: Performed stress analysis on aircraft wing components, utilizing advanced tools to resolve critical issues, contributing to improved reliability and safety.
• Supporting Full-Scale Wing Tests: Acted as a focal point for full-scale wing tests and Transfer of Work activities, demonstrating leadership in coordinating complex projects under tight timelines.

Responsibilities:

• Developing Automated Testing Tools: Built a Matlab tool using Object-Oriented Programming to automate testing of aircraft cabin models.
• Training and Documentation: Created test reports, training materials, and provided training for new employees on model development, supporting consistency and knowledge sharing within the team.