🏆 Top 3% Freelancer on Upwork | AI, Data, and Automation Specialist Hi I'm Marco 👋 I'm a Python developer with over 4 years of hands-on experience building AI systems, automation workflows, and data-driven applications for clients across multiple industries. 🌍 I speak: English, French, Spanish, and Portuguese. 🤖 I use: Cursor, Claude, Hermes Agent. ⭐ Highlights ↳ Developed 5+ MVPs that successfully secured funding. ↳ Completed 45+ Upwork contracts with a 100% Job Success Score. ↳ Built and currently maintain scalable data pipelines for 3+ companies. ↳ Built production-ready Retrieval-Augmented Generation (RAG) systems using modern LLM frameworks and vector databases. ↳ Trained 4+ founders and teams on implementing AI agents. ↳ Configured and deployed Hermes Agent workflows for multiple companies, following security and scalability best practices. ↳ Built custom automation systems powered by LLMs and generative AI for content creation, including avatar videos, images, and social media workflows. ↳ Built 30+ web scrapers on Apify. 🧠 Skills & Tools ↳ AI & RAG Systems: LangGraph, LangChain, OpenAI, ChromaDB, Pinecone. ↳ Hermes Agent: setup, debugging, create custom AI Workflows, Skill integration, Gbrain, MCPs, security best practices. ↳ Automation & Scraping: Playwright, BeautifulSoup, Apify (Actors), Camoufox. ↳ Data Science & ML: Pandas, NumPy, Scikit-Learn, PyCaret, TensorFlow, MMM (Marketing Mix Model), NLP, Optuna. ↳ Dashboards & Visualization: Plotly Dash and Data Studio. ↳ Web Development: FastAPI, Flask, CSS, HTML, Jinja2, Vibe-coding. 🚀 Side Projects ↳ Social Media Automation with Hermes Agent Built 3 custom AI workflows with 7+ integrated skills to automatically generate and publish avatar videos, infographics, and articles on X. ↳ AI Assistant (RAG) for Crypto & Blockchain News Developed a RAG system that continuously ingests, embeds, and retrieves content from multiple crypto and blockchain news sources. ↳ Web3 Analytics Dashboard (Hackathon Winner – €5k Prize) Won a hackathon challenge by building an interactive Plotly dashboard to visualize tokenized assets and blockchain analytics. ↳ AI-Generated Illustrated Books Pipeline Created an end-to-end content generation pipeline that automatically produces illustrated books using generative AI, from story generation to image creation and final assembly. ↳ Enterprise Data Pipelines & Reporting Built and maintained data pipelines connecting APIs, databases, and web scraping systems to analytics dashboards and automated reporting workflows. If you're looking for someone who can build AI applications, automate business processes, develop scalable data systems, or turn an idea into a working product, let's talk. 🤝

I help businesses turn complex data into clear forecasts and executive dashboards. With 10+ years of experience in data science and machine learning, I specialize in: ✔ Time series forecasting (demand, sales, operational metrics) ✔ Predictive modeling & anomaly detection ✔ Interactive dashboards (Power BI / Python) ✔ Data cleaning & transformation ✔ End-to-end ML workflows In my previous role, I improved operational efficiency by 20% and reduced production time by 30% through predictive analytics and AI-driven optimization. If you need: Sales forecasting Inventory prediction KPI dashboards Data automation Model development & deployment guidance I can deliver clean, documented, and decision-ready solutions. Let’s turn your data into a competitive advantage.

🚀 7+ Years of Engineering Excellence: Delivering enterprise AI ecosystems and high-throughput backends across the USA, Europe, Asia and Africa. 🏆 Architect & Founder: Startup founder (AkwaCash) with a $60K+ proven track record on Upwork for building systems that handle tens of thousands of concurrent transactions. ⚙️ The Engineering Focus: I architect production-grade, asynchronous backends for mission-critical workflows. I specialize in integrating AI with stable, scalable enterprise software. 🚀 Founder of JoAmpsConsult 🧩 Fast communication • Clear documentation • Production-ready results ⚙️ WHAT I DO 🔹 Agentic Systems & Orchestration Architecting multi-agentic systems for autonomous reasoning and complex decision-making. I specialize in designing workflows and standardized communication protocols that enable autonomous task completion and system-wide integration. 🔹 High-Performance Backend Engineering Designing distributed, asynchronous architectures optimized for massive concurrency, strict security, and uptime. I build the robust infrastructure and data processing layers required to scale intelligence-driven applications. 🔹 Advanced RAG & Data Engineering Engineering high-precision retrieval systems using hybrid search patterns and complex ETL pipelines. I focus on building grounded, hallucination-free systems that integrate structured and unstructured data sources for enterprise-grade reliability. 🔹 Real-Time Voice AI Systems Building low-latency conversational voice agents using streaming pipelines. I design systems that handle turn-taking, interruptions, and dynamic tool usage, enabling natural, human-like interactions for use cases like support, sales, and scheduling. 🔹 MLOps & Production Rigor Implementing rigorous evaluation frameworks and system-wide observability to ensure services are observable, cost-efficient, and enterprise-ready. I specialize in automated testing, performance benchmarking, and proactive drift monitoring. 🧠 TECH STACK Languages & Frameworks: Python, FastAPI, Flask, LangChain, LangGraph, PyTorch, Hugging Face, TensorFlow, Scikit learn, Pandas, numpy Databases: PostgreSQL, MySQL, MongoDB, Redis, Pinecone Cloud & MLOps: AWS, GCP, Docker, CI/CD, MLflow, W&B, GitHub actions Data Engineering: Airflow, Spark, ETL, Pub/Sub NLP: Text classification, NER, semantic search, embeddings, transformers (BERT, RoBERTa, etc.) Generative AI: GPT models, Gemini, LLaMA, Mistral, RAG, Guardrails, Evaluation Frameworks 💼 WHY CLIENTS HIRE ME ✅ Production-grade AI systems, not prototypes ✅ Deep understanding of both AI + engineering sides ✅ Building robust backend systems ✅ Architecting solutions from the ground up ✅ Clean, scalable code & documentation you can maintain ✅ Fast response time & proactive communication ✅ 100 % focus on measurable business impact ______________________________________________________________________________ KEYWORDS: AI Engineer, Machine Learning Engineer, LLM, LangChain, LangGraph, Hugging Face, RAG, Generative AI, Backend Developer, FastAPI, Python, MLOps, Cloud AI, AWS, GCP, Docker, Kubernetes, Pinecone, NLP, Vector Database, Chatbot Development, Redis, Postgresql, MongoDB, AI Automation, API Development, Agents, Agentic, VoiceAI, voice ai

I’m an AI Developer with an MSc in Artificial Intelligence and a BSc in Computer Science, specializing in building intelligent, data-driven systems. My focus is on applying AI techniques to create practical, scalable solutions for real-world problems. I have hands-on experience in Machine Learning, Deep Learning, and Natural Language Processing using frameworks such as TensorFlow, PyTorch, Scikit-learn, and Hugging Face Transformers. I also develop LLM-based applications with LangChain, RAG, and AI agents, integrating these into production-ready systems. ✅ Core Expertise: • Machine Learning (Regression, Classification, Clustering) • Deep Learning (CNNs, RNNs, Transformers) • Natural Language Processing (Chatbots, Text Mining, Summarization) • LLM Applications – RAG, LangChain, AI Agents, Vector Databases, OpenAI API • Model Optimization, Data Engineering, and Deployment • Python, TensorFlow, PyTorch, Scikit-learn, Pandas, NumPy If you’re looking for a skilled AI developer who can design, train, and deploy intelligent systems, let’s collaborate and bring your ideas to life!

I have experience of working with nearly everything inside and outside of programming domain. All of my external ventures have had the pleasant effect of allowing me to make connections where most people don't even think to look, and make use of all of my skills to the best of my abilities. I absolutely love thinking outside of the box, and most of my personal projects are just a touch crazy in general; I call them creative. Tech buzzwords: - Python (2, 3x), FastAPI, Flask, Celery, asyncio, Django, multithreading/multiprocessing, pytest, unittest; - Databases: PostgreSQL, MongoDB, Redis, ORMs (SQLAlchemy/Alembic, Django ORM - Web: WebSockets, gunicorn, Nginx, a bit of JavaScript/CoffeeScript/Angular, HTML/CSS; - DevOps: Terraforms, Kubernetes, Docker/docker-compose, Linux, deployed things to AWS, DigitalOcean and Heroku; - Machine learning related: Pandas, NumPy, did an API around a TensorFlow model. - AI/ML, NLP, RAG, LLM, LSTM, AGI, RNN, Transformers Usually, I develop individual Python script for each scraping task, so I can adapt my program to any website and deliver output data in different formats(CSV, XLS, JSON, text, database). My scripts can extract data from websites with JavaScript/AJAX, use proxies, solve captchas via 3rd party services, use multi-threading. I have proficiency to setup scripts on Digital-ocean or AWS server. Freelancing is my main source of income, so I pay a lot of attention to my clients, available to respond throughout the day and work full days to complete the projects as fast as possible. I tend to be extremely straight forward about what I can do and how long it might take me to do it. I know my limits, and I try to break past them every single day. Definitely won't be disappointed if given a chance to work together.

Expert Vetted by Upwork - Top 1% Talent -Lead Machine Learning Engineer and Data Scientist with a proven track record in delivering NLP and LLM-driven systems from conception to production and beyond. Skilled in addressing data quality challenges, performing model fine-tuning, and building bespoke data pipelines and evaluation flows. Expert at automating business processes, enhancing precision and speed, while reducing costs.

If you’re looking for an AI engineer who can design LLM and NLP systems that actually work in production, I build intelligent assistants, Chatbots, RAG pipelines and document answering tools that deliver accurate, reliable, enterprise grade results. Clients hire me to turn unstructured text, PDFs and domain knowledge into powerful AI systems that answer questions through grounded context. I’ve built LLM applications for EdTech, healthcare, HR and analytics startups across France, Netherlands and Germany. One client described me as “the best AI engineer I’ve worked with on Upwork” after I rebuilt their deep learning pipeline, fixed data leakage and pushed test accuracy beyond 90 percent. How I can help you: • Custom LLM assistants for your domain • Retrieval Augmented Generation (RAG) systems using your internal documents • Document Q&A pipelines for PDFs, reports, multilingual text and structured outputs • Chatbots for customer support, HR, education or internal workflows • Prompt engineering and evaluation frameworks for consistent results • FastAPI based backends, secure API deployment, and lightweight local LLM setups • Multi agent workflows, vector databases and orchestration with LangChain and LangGraph Tech I work with: Python, LangChain, LangGraph, HuggingFace, OpenAI API, FastAPI, FAISS, Chroma, PyTorch, TensorFlow, Google Cloud, Vertex AI, DeepL, SQLAlchemy Some results I’ve delivered: • Built a RAG system for medical text extraction that improved retrieval accuracy by 40 percent • Developed a multilingual document Q&A bot with memory and structured outputs adopted by analysts • Created an HR assistant with prompt versioning and evaluation tools that reduced response time 60 percent • Delivered AI assistants for educators that automate content review and student response analysis Why clients work with me: • Clean, documented, production ready engineering • Clear communication with both technical and non technical teams • Realistic timelines and solutions grounded in practical deployment • Experience in healthcare, EdTech, HR and enterprise document Let’s get started: Share your problem and a sample of your data. I’ll map out a simple action plan, suggested architecture and timeline so you know exactly how we’ll approach it. Keywords: LLM, NLP, RAG, Chatbot, Document AI, AI Automation, LangChain, LangGraph, Vector Database, Custom AI Assistant, Python, FastAPI, OpenAI.

I’m a Healthcare AI Engineer and Machine Learning Engineer helping Healthcare & MedTech teams build production-ready Medical AI and Clinical AI systems for medical imaging and biomedical signal processing (ECG, EEG, PPG). My focus is not just model accuracy, but clinical validation, deployment, and real-world reliability. If your healthcare AI works in notebooks but struggles in production, I help bridge that gap. What I Help With (Common Healthcare AI Projects) ✔ Medical Imaging AI (X-ray, MRI, CT): disease detection, segmentation, screening ✔ Biomedical Signal Processing (ECG, EEG, PPG): classification, prediction, monitoring ✔ Deep Learning for Healthcare: CNNs, Transformers, time-series ML ✔ Deployment-Ready Machine Learning: FastAPI, Docker, cloud-ready inference ✔ Model Validation & Error Analysis for clinical and research use Results & Proof ✔ Built ECG-based glucose prediction system using PPG data (5★ Upwork project) ✔ Developed non-invasive blood pressure estimation model using clinical signals ✔ Delivered medical imaging deep learning models achieving 92%+ accuracy ✔ Published peer-reviewed EEG research (IJSER, 2021) in biomedical signal AI How I Typically Start Healthcare AI Projects Step 1: Data & requirement review (feasibility, risks, validation scope) Step 2: Baseline model + clinical validation plan Step 3: Production-ready AI pipeline (API, deployment, monitoring) Message me with your dataset and goal I’ll suggest a clear, low-risk roadmap for your healthcare AI project.

Experienced in: 1. Computer vision • C++, Python, OpenCV, CUDA, Git, Linux, Qt, Boost, OpenGl, PCL, Strong math background, Neural Networks - road segmentation for unmanned vehicles (ENet, Caffe, OpenCV, C++, Linux) - car tracking (Yolo v3, OpenCV, C++, Linux) - wagon number identification (Yolo v4, Python) - implementation of real time 360°/perspective camera transformation on Cuda (C++, Cuda, OpenCV, Linux, Jetson Nano) - distance calculation to point on 2D camera frame (C++, OpenCV, Linux) - automate grading system for handwritten answer sheets (computer vision part, OpenCV, Java, Android Key stack: Linux, C++ (Qt), Python, Java, OpenCV, Yolo (darknet) 2. Machine Learning Machine learning research projects in the following domains: - person segmentation (ModNet, RVM, TDNet, UCTransNet, XMem etc.) - image inpainting (Pen-Net, Deepfillv2, Shift-Net, ViNet etc.) - image upscale (RDN, RRDN, Stable Diffusion, ISR etc.) - image relighting (Total Relighting, DPR, RelightNet etc.) - road segmentation for unmanned vehicles (ENet, Caffe, OpenCV, C++, Linux) - car tracking (Yolo v3, OpenCV, C++, Linux) - wagon number identification (Yolo v4, Python) - implementation of real time 360°/perspective camera transformation on Cuda (C++, Cuda, OpenCV, Linux, Jetson Nano) - distance calculation to point on 2D camera frame (C++, OpenCV, Linux) - automate grading system for handwritten answer sheets (computer vision part, OpenCV, Java - Android, IOS - Swift) Key stack: Linux, Python, Pytorch, Tensorflow, OpenCV, Pillow, Numpy, C++, CUDA, Darknet, SegNet 3. Robotics and Embedded development: - OCPP Protocol, Linux, Modbus, Raspberry Pi, CAN; -ROS Robot operating system; - Skilled in SLAM, localization, mapping - Experienced in path planning algorithms, obstacle avoidance, holonomic, and non-holonomic motion planning, trajectory planning for robotics arms; - Used to work with Bayesian/Kalman filters, and sensor fusion (LiDAR, IMU, Visual, Odometry, Radar, GPS). 4. Android development (Kotlin, Java, Android Studio, Eclipse, Firebase). Has expert colleagues in: • .Net Framework (C#, VB.Net, ASP.Net, .Net Core, WPF, UWP,WCF, ADO.Net) • Java (j2se, j2ee, servlets, java beans, Maven) • JavaScript (Node.JS, Express.js, Vue.js, Element.js, Angular.js, D3.js) • C++ (TCP/IP, HTTP, HTTPS, WebSocket, Modbus) • Python (MAVLink, WebSocket) • Step7 (S7 Communication, OCPP, Modbus, CANOpen, ProfiNet) Database • PostgreSQL • MySQL • MongoDB • Microsoft SQL • Oracle Database • Neo4J Software development for mobile platforms • Crossplatform React Native, Flutter, Xamarin, • Android (Kotlin, Java, Android Studio, Eclipse) • iOS (Objective C, Swift) Mobile apps development: • Crossplatform: Futter, React Native, Xamarin. • Android (Java, Kotlin) • iOS (Objective C, Swift) 1. Native Development - Kotlin/Java - Swift / Objective-C - iOS/macOS/tvOS/watchOS - Firebase, CloudKit, Coredata 2. Cross-Platform and Hybrid App Development - React Native/React - Flutter / Dart - Xamarin.iOS / Xamarin.Android / Xamarin.Forms tech stack ● Android Studio, Gradle, Kotlin DSL, KSP ● Kotlin, Java programming languages ● AndroidX, Android Jetpack libraries, Android Architecture Components ● Jetpack Compose ● Material Design Components ● Clean Architecture, SOLID design principles ● MVVM, MVI, GoF design patterns ● Modularization (multi-module projects) ● Kotlin Coroutines + Flow, RxJava, RxBinding ● REST API / Networking - OkHttp, Retrofit 2, Socket IO ● Room Database, SQLite, Datastore ● Kotlinx Serialization, Protobuf, Moshi, Gson ● Dependency Injection (Hilt, Dagger 2, Koin) ● Git ● Firebase Products, Google Cloud APIs, HMS Services ● Admob, Google Play Billing Library (in-app purchases), Samsung/Huawei IAP ● Unit / Instrumented (UI) tests ● Agile Scrum development methodology ● CI/CD (GitHub Actions) AR/VR: Vuforia ARkit/ARcore/AR Foundation Wikitude Oculus Integration OpenXR XR Interaction toolkit VR Walkthrough UltimateXR VR Interaction Framework Hardware expert: • Nvidia Jetson Nano, TX2, Xavier; • Raspberry Pi; • Arduino, STM32; • Depth cameras Intel Realsense d435i , Zed Sterelabs. • Lidars, Radars. Charging stations for the Electric Vehicles development software for the managing stations and networks (server and user applications): • C#, SQL, PostgreSQL, .Net Core, REST Api, WebSockets • OCPP Protocol, Linux, Modbus, Raspberry Pi Software development • .Net Framework (C#, VB.Net, ASP.Net, .Net Core, WPF, UWP,WCF, ADO.Net) • Java (j2se, j2ee, servlets, java beans, Maven) • JavaScript (Node.JS, Express.js, Vue.js, Element.js, Angular.js, D3.js) • C++ (TCP/IP, HTTP, HTTPS, WebSocket, Modbus) • Python (MAVLink, WebSocket) • Step7 (S7 Communication, OCPP, Modbus, CANOpen, ProfiNet) Database • PostgreSQL • MySQL • MongoDB • Microsoft SQL • Oracle Database • Neo4J

Results-driven Software Engineer currently pursuing a dual State Engineer and Master’s degree in AI & Data Science at ESTIN. With over 10 custom applications developed as a freelance developer, I have increased client operations by up to 30% through tailored solutions for diverse industries, such as clothing stores and barbershops. Proficient in technologies including Flutter, React, and Go, I have built complex full-stack applications like a Zoom clone and cinema system. Fluent in Arabic, English, and French, I bring a multicultural approach to problem-solving. Certified in Google Cloud and Docker, with a commitment to continuous learning and delivering impactful digital solutions.