Enis BILICAN

Embedded Software & Critical Systems Engineer

EMBEDDED SOFTWARE AND CRITICAL SYSTEMS ENGINEER - FN Herstal - 01/2023 TO 10/2023 - 04/2025 TO NOW

Context of the project

FN Herstal is a worldly famous defense and security company. Specialized originally in gun manufacturing, they now develop innovative and complex defense systems. Contribution to the software development and integration of a complex critical defense system involving embedded software, HMI, cameras, communication layers and electromechanical subsystems. The project required close collaboration with system engineers, software developers, QA and validation teams to deliver reliable software components in a constrained hardware environment.

Achievements

Contributed to software design, C++ development, system architecture, SCADE model development, HMI implementation and embedded Linux integration. Supported the integration of software components with electromechanical systems, communication layers and validation activities.

Details

✓ Created the main HMI proof of concept in C++ with Qt and contributed to the final HMI implementation with Ansys SCADE Display.

✓ Developed confidential C++ and Python algorithms for system configuration, communication layers and AI-assisted system functions.

✓ Implemented and supported communication interfaces including CAN and TCP/IP between software components and hardware subsystems.

✓ Worked on embedded Linux integration using Yocto and contributed to hardware/software deployment activities.

✓ Co-developed AI-assisted system functions by combining embedded software, camera-based data, configuration algorithms and hardware/software integration constraints.

✓ Contributed to software detailed design, API understanding, functional validation and technical documentation.

✓ Supported QA and validation engineers during User Acceptance Testing, troubleshooting and validation activities.

✓ Coached developers through code review, best practices and system-level understanding.

Team

8 embedded software engineers, 2 QA engineers and a PM

Technical and methodology

C++, native libraries, Boost, Qt, Python, OpenCV, PyQt5, TensorFlow, Ansys SCADE Suite, SCADE Display, Yocto Linux, CAN, TCP/IP, embedded hardware integration, Scrum methodology.

Trainer in Digital Technologies

Training creator and provider in Digital Technologies - HSO Geneve, Otofacto, GSK - 01/2021 TO NOW

Context of the Project

Design and delivery of applied training programs to help engineering, operational and business teams adopt digital technologies, AI tools, industrial vision systems and productivity workflows. The objective was to bridge the gap between advanced technologies and practical day-to-day usage.

Achievements

Supported multiple organizations in adopting AI-based analysis systems, industrial vision tools and productivity workflows. Trained engineers, project managers and administrative teams on AI tools, ChatGPT, Copilot, Microsoft 365 and automation-oriented methods, with a focus on practical implementation and measurable efficiency gains.

Details

✓ Industrial Vision Systems: Trained 25 professionals including managers, engineers and quality leads on fundamentals, algorithm optimization and troubleshooting.

✓ AI for Visual Defect Detection: Coached 12 pharmaceutical engineers on ML model development, testing and deployment logic for quality control.

✓ Trained HR, administrative and operational teams on LLM-assisted agent workflows using ChatGPT and Copilot for AI-assisted automation, documentation support, data analysis, task automation and daily workflow optimization.

✓ Project Management & Microsoft 365: Delivered advanced training for engineers on planning, monitoring, collaboration and Copilot-assisted productivity.

✓ AI-Enabled Machine Implementation: Delivered a 3-day international training for 21 engineers and regulatory managers, covering technical integration, IT constraints, compliance and practical deployment.

Team

Engineers, project managers, specialists, technical teams, HR professionals and administrative staff from various sectors including manufacturing, IT, defense, pharmaceuticals and higher education.

Technical and Methodology

Industrial Vision: Market analysis, production line implementation. AI Tools: Python, TensorFlow, ChatGPT, Copilot. Productivity Tools: Excel, VBA, Project, Teams, Word, PowerPoint, Outlook. Methodology: Interactive workshops, personalized coaching, applied case studies.

Automatic Visual Inspection (AVI)

AI PROJECT ENGINEER & WORKSTREAM LEAD - Takeda - 04/2024 TO 04/2025

Context of the project

End-to-end implementation from scratch of a complex Automatic Visual Inspection system to improve quality control for multiple biological product formats. The system involved 17 camera stations, robotic handling, AI-ready infrastructure, GPU-based processing, vision equipment and industrial IT integration to support high-precision defect detection in a regulated pharmaceutical environment.

Achievements

Led the AI, IT and Vision workstream of the Automatic Visual Inspection (AVI) project, acting as the technical lead for requirements definition, specification writing, supplier coordination and project execution. Coordinated the integration of 17 camera stations with robotic handling, AI infrastructure, vision systems and IT architecture. Organized technical workshops, conducted supplier reviews and factory visits in Italy & France, and ensured alignment between production, QA, engineering teams, senior management, global stakeholders and machine vendors. Oversaw AI deployment requirements, data management, validation expectations, GPU infrastructure sizing, vision algorithm optimization and compliance with pharmaceutical regulations throughout the project lifecycle.

Details

✓ Led the AI, IT and Vision workstream for the deployment of an Automatic Visual Inspection system across 17 camera stations with robotic integration.

✓ Managed the upstream project phase, including requirements collection, technical scope definition, specification writing, supplier clarification and project execution follow-up.

✓ Reviewed and improved supplier vision algorithms through threshold calibration, false-positive reduction and defect detection sensitivity analysis.

✓ Managed the sizing and validation of GPU-based processing infrastructure for real-time AI inference and parallel image processing.

✓ Defined IT integration requirements including data retention, storage strategy, network routing and interoperability with manufacturing systems.

✓ Led the definition of defect taxonomy, inspection performance criteria and AI model evaluation logic.

✓ Coordinated workshops with production, QA, engineering teams, global management and external vendors.

✓ Reviewed supplier technical proposals, challenged design choices and followed up technical actions with machine vendors.

✓ Contributed to inspection method standardization and validation strategy in alignment with pharmaceutical quality requirements (USP <1790>).

Team

1 Project manager, 1 team manager, 4 process engineers, 1 IT infrastructure manager, 1 Computer systems manager, 2 QA, 2 QV.

Technical and methodology

MS Project, Python, PyTorch, computer vision, AI-based visual inspection, GPU processing infrastructure, Digital Twin Visual Components 4.6, Brevetti Vision configuration, Prometheus digital twin, pharmaceutical validation, USP <1790>.

Real-Time Image Processing & LiDAR Engineer

EMBEDDED SOFTWARE ENGINEER - REAL-TIME IMAGE PROCESSING & LIDAR - Arcelor Mittal - 10/2023 TO 04/2024

Context of the project

In a context of human security and quality optimization. Development of internal machine vision and LiDAR-based solutions to improve industrial quality control, operator safety and production efficiency in metallurgy. The objective was to inspect large products directly on production lines, reduce downtime and improve measurement reliability.

Achievements

Developed real-time image-processing and LiDAR-based software using existing 2D cameras to perform aspect and shape inspections from a distance of 5 meters. Implemented algorithms for real-time measurement of length, thickness, shape format, straightness, squareness and convexity. Developed RTSP-based image and data streaming solutions for integration with plant HMIs. Integrated and configured a LiDAR system from scratch for object recognition, shape detection and accurate dimensional measurements, while validating consistency between LiDAR and 2D camera measurements through relative error analysis.

Details

✓ Developed a real-time low-level RTSP video streaming server in C with GStreamer and FFmpeg to securely stream high-resolution industrial images up to 22000×1080 pixels.

✓ Built Python algorithms for straightness measurement, object detection, data merging, relative and absolute error calculation, image stitching and dynamic camera calibration.

✓ Developed AI feature-extraction logic from 2D image data, enabling advanced analysis of product shape, dimensional deviations and background stabilization.

✓ Integrated LiDAR data with 2D camera measurements to improve product shape detection, thickness estimation and quality-control precision.

✓ Developed C++ 3D object detection logic based on LiDAR data preprocessing and industrial sensor integration.

✓ Improved measurement reliability by comparing camera-based and LiDAR-based results and calculating relative errors.

Team

2 embedded software engineers and the R&D technical leader.

Technical and methodology

C with GStreamer and FFmpeg (RTSP server), C++ (3D object detection), Python, OpenCV, Boost, Git. LiDAR drivers, RTSP streaming, sensor fusion, real-time image processing.

Pharmaceutical machine vision

PROCESS AND MACHINE VISION ENGINEER - GSK (GlaxoSmithKline) - 03/2022 TO 12/2022

Context of the project

GSK (GlaxoSmithKline) is a leading pharmaceutical and vaccine manufacturer. Within the Filling and Visual Inspection (FVI) department, the objective was to optimize automatic visual inspection systems for syringes and vials to reduce false rejects while maintaining defect detection performance. The scope covered product defects (particles, foreign objects) and container defects (cracks, scratches, glass defects). The environment included more than 50 machine vision programs across 4 production lines operating under GMP requirements.

Achievements

Developed, optimized and validated machine vision algorithms across 4 production lines to improve inspection reliability and production efficiency. Enhanced lighting systems, camera configurations and inspection parameters to achieve the optimal balance between sensitivity and false reject rates. Ensured the proper operation of inspection equipment from software, hardware and algorithmic perspectives while complying with GMP, hygiene and safety requirements. In parallel, launched and led a Pharma 4.0 standardization initiative aimed at harmonizing more than a decade of independently developed inspection algorithms.

Details

✓ Optimized lighting systems, camera settings and inspection thresholds to reduce false rejects while maintaining high defect detection performance.

✓ Ensured reliable operation of automatic visual inspection equipment through troubleshooting, corrective actions and preventive maintenance.

✓ Led the standardization of machine vision algorithms by comparing historical detection methods, identifying best practices and promoting harmonized inspection strategies across products and production lines.

✓ Conducted production performance monitoring through KPI analysis, trend evaluation and continuous improvement initiatives.

✓ Led deviation investigations and Problem Solving Sessions (PSS) using Six Sigma methodologies, 5 Whys analysis and Root Cause Analysis.

✓ Participated in continuous improvement projects including technical analysis, business case preparation, planning and implementation.

✓ Contributed to validation and qualification activities (IQ, OQ, PQ) and GMP-compliant documentation.

Team

5 engineers in process and vision, 2 QA and 3 technicians.

Technical and methodology

Seidenader machine vision programming, ImageJ, VBA, Python, VMware, Six Sigma, 5 Whys, Root Cause Analysis, GMP, IQ/OQ/PQ, KPI monitoring.

LiDAR Integration for Autonomous Driving R&D

DATA POST PROCESSING ENGINEER - AGC - 10/2021 TO 02/2022

Context of the project

R&D project focused on LiDAR sensor integration behind automotive windshields. The objective was to process, standardize and analyze 3D LiDAR point-cloud data to evaluate optical performance, support sensor behavior analysis and explore AI-based spatial data interpretation. This allows to model the environment accurately, which is the first step towards the development of self-driving cars.

Achievements

Developed LiDAR data reception, parsing and post-processing algorithms with a focus on robustness, standardization and near real-time processing. Supported the integration of multiple LiDAR sensors using TCP/IP communication and AGC-specific analysis protocols. Contributed to AI-based analysis of 3D spatial data using mathematical representations of points, distances and geometric relationships within point clouds.

Details

✓ Developed LiDAR data reception, parsing and standardization algorithms for automotive sensor R&D.

✓ Built a robust TCP/IP communication and data-processing workflow to integrate multiple LiDAR sensors into AGC analysis protocols.

✓ Implemented self-diagnostic logic to improve reliability in test conditions where live debugging was limited.

✓ Created dynamic parsing procedures for point-cloud data extraction, standardized data storage and near real-time analysis.

✓ Developed mathematical processing algorithms for 3D point-cloud analysis, including spatial transformations, distance calculations and geometric feature extraction.

✓ Supported AI and deep learning experimentation on 3D LiDAR data for object characterization and sensor performance evaluation.

✓ Tested the algorithm under real conditions with different windshield glass configurations.

✓ Supported deep learning hyperparameter optimization for different windshield materials and sensor configurations.

Team

Multidisciplinary 6 R&D engineers (optical, mechanical, electronic and IT)

Technical and methodology

C# with .NET Framework, Python with TensorFlow, Wireshark for frame analysis, TCP/IP communication, LiDAR software, 3D point-cloud processing, geometric analysis, spatial mathematics, deep learning, near real-time parsing.

Industry 4.0 Vision Solution for Food Manufacturing

INDUSTRIAL IT SYSTEMS ENGINEER - PASQUIER - 09/2020 TO 10/2021

Context of the project

Attached to the Methods, Projects and Industrial IT department. The main theme is the management and development of a new industrial vision solution prototype to guarantee the traceability and sorting of products produced through sharp real-time controls such as volume calculations and colorimetric analysis, as well as data feedback controls on the IS. Full development from scratch as solo engineer, from specification to IT architecture, algorithms, electronics and HMI.

Achievements

Designed and developed both hardware and software components of a mobile vision prototype. Translated production and quality needs into functional specifications, selected the appropriate sensing architecture and implemented algorithms for volume and color analysis. Realized a working mobile prototype for machine vision controls that can be moved from line to line to try different product families and allow deployment on all factory lines.

Details

✓ Led the design and deployment of an Industry 4.0 machine-vision solution, proposing technical improvements and alternative architectures for product traceability, sorting and quality control.

✓ Collaborated with Quality Assurance and Mechanical Design teams to translate operational needs into functional specifications and select the most suitable vision-system architecture.

✓ Developed real-time Python/C++ algorithms for 3D volumetric measurement using triangulation sensors, including point-cloud processing, dynamic adaptation to multiple product formats and reliability monitoring.

✓ Designed advanced color-analysis algorithms based on the CIELAB color space and DeltaE metrics to assess product cooking consistency, while optimizing lighting and environmental conditions.

✓ Implemented data formatting and communication workflows to exchange information between software processes and industrial databases.

✓ Designed and built a mobile industrial prototype integrating 3D sensors, vision hardware, processing algorithms, .NET-based HMI, electrical systems and custom mechanical housing.

✓ Implemented automated calibration procedures and delivered training sessions to technicians, enabling efficient adoption and long-term operation on production lines.

Team

Operational and Industrial IT department

Technical and methodology

Python with NumPy, OpenCV, Colour-Science modules, C++, ImageJ, .NET HMI, 3D sensor SDK, database communication, AutoCAD electrical design.

Connected and ventilated face mask

ELECTRONICS AND EMBEDDED ENGINEER - 10/2020 TO 04/2021

Context of the project

Development of a connected ventilated mask prototype integrating embedded control, airflow regulation, BLE communication and Android-based monitoring, as an end-of-study project.

Achievements

Designed a first functional prototype combining a 3D-printed structure, Arduino-based embedded control, PWM fan regulation, differential pressure sensing and BLE communication with a native Android application.

Details

✓ Conducted technology benchmarking and market analysis to identify existing solutions and evaluate public-market constraints.

✓ Developed an embedded control algorithm using a differential pressure sensor to compare internal and external mask pressure and dynamically adjust fan speed as well as opening and closing cycles, avoiding imposed breathing rhythms.

✓ Optimized comfort and autonomy through energy-management strategies, battery sizing and mass-distribution analysis.

✓ Designed the mechanical structure in Autodesk Inventor for 3D printing, ensuring flexibility, user comfort and cable routing through a dedicated 'spider-web' architecture.

✓ Designed the electronic architecture around an Arduino Nano platform, selecting and sizing components for safe operation, integrating protection resistors and capacitors to minimize electrical disturbances.

✓ Implemented Bluetooth Low Energy (BLE) communication between the embedded system and an Android application for configuration and monitoring.

✓ Developed Android application features allowing users to configure ventilation modes, switch between automatic and manual fan-speed control, and visualize operational statistics through dashboards.

Team

Binomial with another IT Engineer

Technical and methodology

Arduino C, BLE communication, Android Studio, Java, XML, PWM control, differential pressure sensor, Autodesk Inventor, 3D printing, Fritzing, electromagnetic disturbance management.

Connected smart home

IT ENGINEER - 10/2019 TO 06/2020

Context of the project

Design and development of a connected smart-home ecosystem aimed at controlling household equipment through a mobile application while evaluating multiple industrial and consumer communication protocols. The project focused on interoperability between heterogeneous devices, embedded systems and cloud-connected services.

Achievements

Designed the overall system architecture, integrating embedded controllers, wireless communication technologies and user-facing applications. Evaluated and implemented several communication protocols to ensure reliable connectivity, scalability and interoperability between devices.

Details

✓ Developed a cross-platform mobile application to monitor and control connected devices from a centralized interface.

✓ Implemented BLE communication between embedded devices and the mobile application for local control and configuration.

✓ Integrated Z-Wave technology through a gateway architecture to manage smart lighting systems.

✓ Developed REST API interactions to exchange data between connected devices, gateways and external services.

✓ Implemented LoRaWAN connectivity for long-range, low-power communication scenarios.

✓ Configured MQTT-based messaging to enable event-driven communication and real-time device status updates.

✓ Designed and tested end-to-end communication workflows involving multiple protocols and heterogeneous devices.

Team

Solo development

Technical and methodology

Arduino C, WinDev, BLE, Z-Wave (REST API), LoRaWAN, MQTT, mobile application development, embedded systems, IoT architecture.

Connectivity for IOT sensors

DATA AND IOT ENGINEER - 10/2019 TO 01/2020

Context of the project

Development of an end-to-end Industrial IoT monitoring platform dedicated to environmental data acquisition, processing, storage and visualization. The objective was to transform raw sensor measurements into actionable insights through automated data pipelines and interactive dashboards. Establishment of 2 kinds of communication: server-client connection and messaging dialogue. Exploitation of data in 2 different IIoT platforms to prove data is not pre-formatted for specific applications and is easily integrable.

Achievements

Designed and implemented the complete data lifecycle, from sensor acquisition and preprocessing to database storage, analytics and visualization. Focused on data reliability, scalability and real-time monitoring capabilities.

Details

✓ Integrated temperature and humidity sensors with a Raspberry Pi platform to create a low-cost industrial monitoring solution.

✓ Developed Python data-processing pipelines using NumPy and Pandas for data cleansing, aggregation and formatting.

✓ Implemented MQTT and REST-based communication services to support reliable data collection and transmission.

✓ Designed a time-series storage architecture using InfluxDB for historical analysis, trend monitoring and data retention.

✓ Created interactive dashboards with Dash to visualize live measurements, system status and configuration parameters.

✓ Implemented automated data acquisition and logging mechanisms to reduce manual intervention and improve traceability.

✓ Validated end-to-end data flows from sensor acquisition to visualization and reporting.

Team

Solo development

Technical and methodology

Python with NumPy, Pandas, Matplotlib, Dash modules, REST API, MQTT, InfluxDB, Raspberry Pi, time-series databases, data pipelines, sensor integration, Fritzing.

This website, Flask based on Raspberry PI

SOFTWARE & WEBSERVER ENGINEER - 06/2023 TO NOW

Context of the project

The project involves the creation and management of a personal website hosted on a Raspberry Pi running Ubuntu Server 22.04 LTS. This website is designed to comprehensively showcase my work, professional experience, educational background, and freelance solutions. Opting for the Raspberry Pi and Ubuntu Server reflects my aim to demonstrate the feasibility of deploying effective web solutions on low-cost hardware. Utilizing Apache as the web server and Flask for backend development, I have implemented a dynamic web application that manages user sessions, data display, and provides an interactive interface. A significant feature of the site is its language management, which is handled through an integrated file-based translation system. This system allows users to navigate the site in multiple languages seamlessly without requiring page reloads. This multilingual capability enhances the site's accessibility and appeal to an international audience.

Achievements

One of the major achievements of this project was the successful deployment of a web server on a Raspberry Pi, proving that cost-effective solutions can be optimized for satisfactory performance. By developing a web application with Flask, I created a dynamic user interface that caters to visitors' needs while ensuring smooth data management and session handling. Another notable accomplishment was the integration of a QR code generation feature in real-time without storing them on the server, thereby optimizing storage management. Additionally, I implemented a language management system with file-based translations, facilitating multilingual navigation. Adding contact page with mail sending. Automating server maintenance was also a significant achievement, achieved through the setup of APScheduler to remove outdated temporary files, ensuring ongoing system cleanliness and performance. These accomplishments not only showcase my technical skills in web development and server management but also highlight my innovative approach to delivering an optimal user experience.

Details

✓ Hardware and Software: Deployed on a Raspberry Pi with Ubuntu Server 22.04 LTS.

✓ Server: Port forwarding, reverse proxy, SSL generation and use, domain management with porkbun, uses Apache for web serving.

✓ Backend Framework: Flask is used to build my portfolio dynamic web application.

✓ QR Code Feature: Real-time QR code generation and display without server-side storage. Try www.enis.pro/qr-code .

✓ Language Management: Integrated file-based translation system for multilingual support.

✓ Maintenance Automation: APScheduler setup for automatic removal of outdated temporary files.

Team

Solo development

Technical and methodology

PYTHON (Flask, Flask Mail, APScheduler, LoggerManager), APPACHE, MICROCONTROLLER RASPBERRY PI, DOCKER