Ayman OUKACHA

Leading the architecture of a GenAI-powered due diligence platform for FinTech, combining semantic knowledge systems, trustworthy AI, and secure infrastructure to improve the reliability, explainability, and usability of AI for financial, legal, and esg analysis. - Architected a modular, event-driven AI platform combining knowledge-augmented generation, agentic retrieval, and knowledge graphs across KYC, AML, ESG, and compliance workflows. - Designed the semantic backbone with RDF/OWL/SHACL, RDF databases, ontology alignment, and LPG-to-RDF translation, enabling standardized and explainable analysis across heterogeneous due diligence data. - Improved entity-to-ontology class linking and optimized NER/entity-linking pipelines, cutting entity and record duplication by 25% and increasing RAG answer accuracy by 10 percentage points on internal benchmarks. - Reduced hallucination and factual error rate by 50% through ontology-grounded retrieval and reasoning. - Built scalable processing flows using messaging queues and a pipeline orchestrator, and designed agentic patterns for both chatbot-style QA and structured enterprise querying. - Implemented agentic workflows using MCP and skills-based tool orchestration to support structured tool use, contextual analysis, and enterprise system interaction. - Optimized the GraphRAG and LLM serving stack, reducing end-to-end batch execution time by 60%. - Improved security, usability, and adoption through microVM-based sandboxing, API hardening, and AI-oriented UI/UX workflow design.

Worked on the design and evolution of Archibus, a React/Spring workplace management platform for large enterprise clients. - Developed full-stack features with Spring, React, and Node.js in a microservices architecture. - Contributed to AWS solution architecture and the migration from bare-metal environments to a cloud-native architecture, with CI/CD automation and secure database operations. - Worked on real-time workspace monitoring, computer vision, and affluence analytics using IoT devices, supporting smarter workplace operations and decision-making. - Contributed to machine learning-based occupancy prediction and intelligent workflow use cases within workplace management applications. - Participated in technical design, client workshops, POCs, documentation, and UI improvements.

Contributed to the design, development, testing, and deployment of a scalable event-driven microservices platform using Spring Boot, DDD, CQRS, Docker, and Kubernetes. - Developed event-driven microservices with Spring Boot, applying DDD and CQRS principles for scalability and resilience. - Contributed to technical design, feature delivery, bug fixing, and code quality through testing and continuous improvement. - Supported containerization, orchestration, and deployment with Docker, Kubernetes, and CI/CD pipelines. - Helped maintain service reliability and production readiness through automated testing and observability practices.

Contributed to industrial solutions combining machine learning for IoT anomaly detection, computer vision, Kafka-based event-driven microservices, and Angular UI/UX for monitoring and operational workflows. - Worked on machine learning and computer vision use cases for industrial process monitoring and anomaly detection. - Developed Spring Boot microservices and event-driven architectures for real-time workflow orchestration. - Applied ML models to IoT and streaming data for anomaly detection and predictive monitoring. - Built Angular applications and dashboards for real-time visualization and user workflows. - Participated in business analysis, user story definition, deployment, and observability across distributed environments.