Adrien Kouki

🚀 Digital transformation of regulatory expertise and marketing claims Developing innovative ML solutions on Google Cloud Platform to revolutionize the experience of regulatory and marketing claims experts worldwide through intelligent internal tools. 🎯 Core Mission: Design intelligent tools that free experts from tedious regulatory framework navigation, enabling focus on high-value claims analysis. ⚡ Key Responsibilities: • ML Pipeline Architecture: Design and maintain industrialized ML pipelines on GCP with scalable infrastructure for global regulatory workloads • Production Deployment: Implement CI/CD for ML models, managing monitoring, maintenance, and performance optimization • Security by Design: Implement cybersecurity best practices protecting proprietary data and critical client information through strategic data sovereignty and internal AI system security • Cross-Functional Collaboration: Transform Data Science prototypes into production solutions while partnering with Reg&Claims experts to translate regulatory challenges into technical innovations • Infrastructure Optimization: Collaborate with DevOps/Data Engineering teams to optimize GCP infrastructure for training, inference, and strategic data management 🎨 Impact: Transforming traditional regulatory processes into engaging, efficient experiences through automated work pre-qualification, significantly reducing administrative overhead. 🔧 Tech Stack: GCP ML Platform, CI/CD MLOps, Internal DevOps Tools, AI Security Architecture, Strategic Data Governance

As a Machine Learning Engineer at Qantev, I actively contribute to developing AI solutions for automated legal document analysis in the insurance industry. I was involved in designing and implementing end-to-end solutions, from digitization (OCR) to database integration, including named entity recognition, prompt engineering. My main contributions include: AI Solution Architecture & Scalability: I helped design the solution's architecture to maximize the efficiency and scalability of AI functionalities, focusing on performance optimization. Generative AI & OCR Integration: I integrated generative AI models (LLMs) and Optical Character Recognition (OCR) technologies to automate the processing and analysis of legal documents, improving data processing efficiency. API Design & Maintenance: I designed and maintained efficient APIs to facilitate access to AI services and models, ensuring their performance and reliability. Data Pipelines & Quality Control: I ensured efficient data pipeline integration with rigorous quality controls to guarantee data integrity and efficient information flow within the system. Collaboration & Tech Watch: I collaborated closely with AI, business, and platform development teams, contributing to technical choices and providing practical and innovative solutions. I also kept up-to-date with the latest AI/ML trends to identify and integrate best practices and emerging technologies. End-to-End Insurance Document Processing Solution: I participated in delivering a complete (end-to-end) solution for analyzing insurance documents, including OCR, named entity recognition, and database integration.

Led a team of 4 data engineers in the development and implementation of supply chain solutions for manufacturing clients in the aircraft, jewelry, and automotive industries. Developed and implemented new deployment protocols, resulting in significant cost savings for clients. Leveraged expertise in modern data engineering tools, including Apache Airflow, Kubernetes, DBT Core, Terraform, and Ansible, to build and maintain robust data pipelines and infrastructure. Utilized Agile project management methodologies, with a focus on clear communication and task management using Linear, to ensure on-time and within-budget project delivery. Improved development processes by revamping CI/CD pipelines using GitLab and implementing IaC (Infrastructure as Code) practices. Collaborated closely with SRE/DevOps teams to ensure the reliability and scalability of our solutions and provided technical support to clients.

As a Senior Platform Data Engineer within the data analytics team, I focused on building and maintaining a robust and scalable data analytics platform. This involved close collaboration with various departments to deliver data-driven insights for key business decisions. We followed lean development principles, emphasizing rapid iteration, feedback loops, and agile methods to create user-focused solutions. My key contributions included: Cloud Cost Optimization & Migration: Reduced cloud infrastructure costs by migrating from a multi-cloud to a single-cloud environment (AWS). This improved system stability and simplified maintenance. I also replaced an in-house data pipeline scheduler with a more efficient and maintainable solution (Apache Airflow), further enhancing reliability and reducing operational overhead. Data Pipeline Engineering & Monitoring: Developed and maintained robust data pipelines for diverse data sources, including Search Engine Advertising (SEA) data from Meta and Google Ads, clickstream user behavior data, and back-office systems data (call center, flights, activities, and user claims). Implemented monitoring and alerting to ensure high availability and performance of these pipelines. Data Warehouse Development & Maintenance: Focused on maintaining the stability and performance of the data warehouse (BigQuery, PostgreSQL). Implemented a cost control feedback loop to optimize resource utilization and prevent performance bottlenecks. Conducted competitor benchmarks to identify areas for improvement in system performance and efficiency. We prioritized open-source tools and cloud-based services (AWS, Google Cloud Platform) for building scalable and cost-effective systems, and I stayed up-to-date with industry best practices for reliability and performance.

At this early-stage ed-tech startup, I combined software engineering with a passion for teaching, empowering tech teachers with cutting-edge tools and resources on our Microsoft Azure platform. Here's how I contributed: Technical Instruction & Mentoring: Led hands-on Machine Learning and Data Engineering training at leading institutions like EFREI, AI School, Ynov, and Simplon, managing classes of up to 50 students. Focused on clear communication and patient instruction to guide novice learners to become confident, hands-on software engineers. Curriculum Development & Content Creation: Developed engaging educational resources and learning modules for the platform, hosted on Microsoft Azure, focusing on practical application and skill-building. Cloud Infrastructure Scaling (Azure): Engineered a custom autoscaler to dynamically adjust instance numbers during peak traffic (hundreds of requests per second across France), resulting in a 30% improvement in system capacity and ensuring platform stability.

Development of a software component for the AMADEA ETL for fraud hotspots detection ✔ Inspired by recent research papers, I designed a new methodolgy according to the specifications ✔ Turned raw transaction records into a transactional graph ✔ Developed and tested a software prototype for Point of Compromise identification (Python/C++) ✔ Integrated the developed component to the company ETL

Robustness analysis of the lateral assist control law of a project of autonomous vehicle ✔ Autonomous driving functions design and improvement(Matlab, Simulink) ✔ Autonomous driving experiments regarding the designed control law (Control Desk) ✔ Presented and documented the accomplished tasks for further development

Development of an automated model validation tool for industrials ✔ Improved a software test bench for various industrial models ✔ Researched about machine learning techniques (Neural nets) ✔ Made reports and gave feedback to the company about experimental improvements

Internship in the “Barn and feeding department” for continuous development of 2-wheeled robot localization functionalities ✔ Set up and experimented the ROS environment (Linux) ✔ Developed tools for 2-wheeled robot navigation (Kalman filter, data fusion) ✔ Visualized real-time corrected trajectory of a robot(Qt Creator, Matlab, ROS) ✔ Wrote a documentation and a ROS tutorial for the engineering team ✔ Gave presentations to the Dutch and Turkish teams