



TATA AI
Tata AI is a mobile app for iOS and Android, optimized for smartphones and tablets, designed for children. By entering 3 keywords and 3 images, artificial intelligence creates personalized fairy tales complete with narrative text, imaginative illustrations, and a voice that narrates the story. It stimulates creativity and imagination, offering unique and engaging experiences for young readers. Easy to use and safe, Tata AI guides children into the world of stories.React nativeIOS App developmentAndroid App developmentOpen AI APIPythonTypeScript
ARRAS HOME
Arras Home is a mobile app for iOS and Android that revolutionizes IoT device management and video surveillance with cutting-edge artificial intelligence. Integrated with Home Assistant, it lets users control smart home devices in real time with interactive voice commands. Advanced machine learning optimizes energy use and provides personalized automation for enhanced security and efficiency. User-friendly and reliable, Arras Home creates a connected, intelligent, modern home ecosystem.React NativeSviluppo App iOSSviluppo App AndroidDockerAWSTypeScriptLangChainTensorFlow & KerasPythonNode.jsHome AssistantDynamoDB
RERANKA MULTI-MARKETPLACE INSIGHTS
Reranka Multi-Marketplace Insights Hub is a powerful e-commerce dashboard integrating real-time sales data and AI technology from platforms like Amazon, eBay, and Zalando. Using advanced ETL processes and a high-speed NoSQL database, it ensures immediate data availability and detailed performance analysis. The platform offers granular insights for precise and personalized sales strategies, helping businesses optimize sales, enhance efficiency, and gain a competitive edge.Node.jsReact.jsPythonExpress.jsTailwind CSSTypeScriptAWSTensorFlow & KerasAWS CodePipelineDynamoDB
AMAZON REAL-TIME BENCHMARK
Amazon RealTime Benchmark is a sophisticated web application designed to monitor the real-time market share of a seller's products on Amazon. It uses advanced algorithms and machine learning to provide insights into sales performance, allowing vendors to compare their market share with competitors. This tool enables active monitoring, competitive benchmarking, and strategic pricing adjustments based on market trends.Node.jsReact.jsNext.jsPythonGraphQLTailwind CSSTypeScriptAWSRedis
mySANIBOT
mySANIBOT is an AI-powered health assistant using OpenAI's 4.0 mini model for wellness guidance. It offers expert health advice, redirects to relevant resources, and provides personalized responses. This chatbot connects users with reliable information and professional guidance. We also capture and store conversations, displaying them in a custom React app for administrators.PHPWordPressAWSReact.jsTailwind CSSNginx serverOpen AI API
AMAZON DISCOVERY
Amazon Discovery unlocks the potential of Amazon's vast marketplace by leveraging the SP API to gather, confirm, and analyze ASIN data. It provides precise market insights and revenue estimates, automates data processing to highlight key trends and metrics, and offers a comprehensive market view, helping businesses elevate their strategies and stay competitive in e-commerce.Node.jsPythonReact.jsNext.jsTailwind CSSTypeScriptAWSNginx serverMongoDBTensorFlow & Keras
TELEGRAM ALERT SYSTEM
The TELEGRAM ALERT SYSTEM is a software designed for daily analysis of sales and online marketing data, identifying critical issues or strategic opportunities. It generates alerts across various business sectors, including sales margins, logistics, stock issues, pricing strategies, and digital marketing. Alerts are sent via Telegram, with a dedicated process for each operator, ensuring timely and targeted responses to emerging challenges and opportunities in online sales management.Node.jsReact.jsExpress.jsTypeScriptAWSDynamoDB
BLOCKVISION | BLOCKCHAIN
BLOCKVISION is a smartphone-optimized web app that certifies the entire production chain with blockchain technology. It offers both a proprietary version and a customizable white-label version. Each client’s page features unique components, fonts, colors, and styles. The app includes advanced functionalities and animations for a modern user experience, showcasing our expertise in creating dynamic, tailored web applications.Node.jsReact.jsNext.jsTailwind CSSTypeScriptAWSGraphQLDynamoDBNginx server
CRONOMEGAWATT
A sophisticated platform for managing construction site activities. Leveraging advanced algorithms and AI, it features a Gantt-style graphical dashboard that enables meticulous planning of construction tasks, prediction of project completion dates, and organization of interdependent tasks with automatic tuning for optimal efficiency. The platform supports multi-level account management and is fully scalable, making it a true SaaS solution that can be marketed to multiple clients.Node.jsReact.jsNext.jsNest.jsTailwind CSSTypeScriptAWSTensorFlow & KerasAWS CodePipelineMongoDB
VISIGEN
VisiGen is an AI system that generates images from textual prompts using advanced diffusion processes. This technology interprets text descriptions and creates corresponding visual content, leveraging deep learning techniques to produce high-quality, realistic images. Ideal for creative and design applications, it showcases the synergy between natural language processing and computer vision. VisiGen is integrated via API with Stability AI Stable Diffusion through Amazon Bedrock.Node.jsReact.jsNext.jsBedrockStability AIAWSNginx server
AI SUPERAGENT + KNOWLEDGE BASE
A truly innovative project featuring an AI model with three core functionalities: advanced LLM for complex queries, AI agent for system interactions, and customizable training via uploaded text documents. Utilizing the RAG technique and integrated with AWS Bedrock this model leverages Claude LLM by Anthropic. Built on a robust architecture, AI SuperAgent delivers unparalleled power and efficiency. It can be integrated with any system to perform human tasks seamlessly.Node.jsReact.jsNext.jsPythonBedrockElasticsearchClaude LLM modelAWSNginx server
VVAULT: ECOMMERCE PLATFORM
VVault is a dynamic and user-friendly eCommerce website featuring a wide range of products across multiple categories. The platform integrates advanced AI for personalized product recommendations, tailored promotions, and an AI assistant, ensuring a seamless and engaging shopping experience for users.PHPLaravelMySqlWordpressNginx serverAWS CodePipelineAWS
CARTELLO EDITABILE - SIGN MAKER
Sign maker is a versatile web application that allows users to create personalized construction site signs with ease. The platform features an intuitive editor for designing custom signage, generates high-resolution PDFs optimized for printing, and integrates an ActiveCampaign module for submitting requests to administrators.React.jsNext.jsTailwind CSSTypeScriptAWSNginx server
PANSCRIBE: BOOK REVIEW WEB APP
Panscribe is a platform for literary review exchange, featuring an Author Panel for real-time analytics and reader interaction control. The Reader Program offers free book access for reviews, integrating smoothly with platforms like Amazon. Simplifying traditional rating systems, it fosters a supportive environment for authors and readers, with a secure, multi-level authentication system for varied subscription privileges.Node.jsReact.jsNext.jsTypeScriptTailwind CSSAWSNginx serverPostgreSQL
MY GITHUB REPOS
In this section you'll find my open source projects that I share with the community. For each project, I've created a YouTube tutorial explaining the core ideas and development logic in detail, guiding developers through the integration of the solutions I present. These projects are experimental and MVP-style, but they are then integrated into real production systems using the same concepts, expanded and refined for enterprise deployment. I firmly believe that if we've achieved incredible milestones in IT today, it's thanks to open source, knowledge sharing, and the developer community. This is my contribution to a better world built on sharing our work.
A production-grade, real-time cyber attack detection system deployed on AWS with automation. Features autoencoder-based anomaly detection, incremental SGD classifier for streaming data, dual training pipelines (batch & streaming), AWS CloudFormation infrastructure, CI/CD, Blue/Green deployments, and attack simulation for DoS, exploits, backdoors & more.
Watch the video
Project repository
The future of document search is here! Vision RAG fuses text and image processing into one powerful RAG workflow. Features dual embedding strategies (OpenAI + Cohere), PostgreSQL with pgvector for semantic search, Docker-first deployment, unified ingestion layer with OCR support, and multimodal answers combining text & images using GPT or Gemini.
Watch the video
Project repository
Demystify LLMs! A visual deep dive into Transformers: self-attention, embeddings, positional encoding, multi-head attention, and feed-forward networks explained intuitively. Then build a text generation model from scratch in Keras tokenization, dataset preparation, training with real metrics, and output analysis. No black boxes, just real code and clear math.
Watch the video
Project repository
Combine vector embeddings and graph databases for intelligent retrieval! Features Neo4j integration, multi-vector embeddings, and advanced traversal algorithms: Context-to-Cypher, K-hop BFS, Depth-Limited DFS, Uniform Cost Search, A* Heuristic, Beam Search all with optional LLM predicate filtering. Includes entity extraction with LangChain and visualization techniques.
Watch the video
Project repository
A comprehensive benchmark of top AI agent frameworks (LangChain, OpenAI Agent SDK, CrewAI, LlamaIndex, AutoGen, Semantic Kernel) vs pure Python. Covers multi-agent orchestration, state management, tool integration, MCP interoperability, code execution pipelines, and guardrails. Each framework scored on abstraction, readability, setup complexity, and flexibility.
Watch the video
Project repository
Why choose between RAG and Text-to-SQL when you can have both? This system combines Traditional SQL for precision, Vector Embeddings for semantic understanding, and Fuzzy Matching for typo tolerance. Features multi-language support, self-healing queries, and SQL injection protection.
Watch the video
Project repository
A Transformer-based time series forecasting model for predicting stock-price signals using TensorFlow and Keras. Features multi-head self-attention, stacked Transformer blocks with residual connections, sliding-window datasets, positional encodings, TensorBoard monitoring, and visualization tools for capturing long-range dependencies in financial time series.
Watch the video
Project repository
A Model Context Protocol server built from scratch using FastAPI, WebSockets, and async/await in Python to understand low-level MCP logic. Features dual-mode operation (HTTP REST and WebSocket), server capabilities (tools, prompts, resources), API-key authentication, and a client agent that converts natural language to SQL queries.
Watch the video
Project repository
SurfAi is an intelligent and lightweight web automation engine that leverages AI to interpret natural language instructions and automate web interactions using Playwright. It combines LLM capabilities with browser automation for complex task execution. For exmample it can book flights, buy things online, or login and create automatic posts on LinkedIn.
Watch the video
Project repository
A Transformer-based LLM implementation featuring Key-Value (KV) Caching and Causal Masking for production-grade text generation. This project demonstrates GPT-style architecture in Python/Keras/TensorFlow with efficient O(n) decoding, dynamic cache updates, causal attention masks, and performance benchmarks showing dramatic speedup compared to vanilla implementations.
Watch the video
Project repository
What happens if you add RAG ingestion/retrieval as tools to AutoCodeAgent? We have AutoCodeAgent 2.0! An intelligent system that can automate ingestion and retrieval in the db to enhance the agent's performance and use them as a subtask tools to solve complex tasks.
Watch the video
Project repository
Fine-tune Google's Gemma 3 1B-IT model for advanced math reasoning using LoRA (Low-Rank Adaptation) and GRPO (Generative Response Policy Optimization). Features Unsloth optimizations for 4-bit quantization, custom reward functions for numeric accuracy and formatting, chain-of-thought structuring with XML tags, and training on consumer-grade hardware. Includes full code walkthrough for dataset preparation, reward shaping, and model deployment.
Watch the video
Project repository
AutoCodeAgent is an advanced AI-powered system that automatically breaks down complex tasks into manageable subtasks, generates and executes Python code for each, and iteratively refines the process. Leveraging cutting-edge AI techniques, it orchestrates the use of various tools and libraries to solve problems efficiently and effectively.
Watch the video
Project repository
A workflow for adapting compact language models to select software tools. Features synthetic data generation for 10,000 query-tool pairs, tokenizer extension with control tokens, TRL's SFTTrainer configuration, 4-bit quantized training on consumer hardware, and continuous evaluation. Uses SmolLM2-135M from Hugging Face.
Watch the video
Project repository
An intelligent system designed to orchestrate and manage a chain of autonomous agents to solve very complex tasks. By decomposing intricate tasks into simpler, manageable sub-tasks, Interactive Multiagent ensures efficient and effective task execution through specialized agents. It's a sort of chain of thought where agents are interacting with each other and the user to solve the task.
Watch the video
Project repository
The AI Blog Generator is a Dockerized system that leverages LangChain, OpenAI's GPT-4, and Hugging Face APIs to create engaging blog articles on trending topics. The workflow includes automated trend analysis, news extraction, detailed article generation, and custom image creation.
Project repository
Sophisticated AI agents depend on workflows managed by state machines. While many open-source libraries exist (e.g., LangGraph), PyTransitions stands out due to its broad functionalities and robust extensions like HierarchicalMachine, GraphMachine, and AsyncMachine, making it an excellent choice.
Watch the video
Project repository
This advanced web app leverages cutting-edge Generative AI, featuring an AI super-agent for web search, data processing, and LLMs. It includes custom AI training, AWS S3 file handling, and real-time communication via Socket.io. Built on Amazon Bedrock with AWS Lambda and OpenSearch integrations, the app delivers smart, scalable, and high-performance solutions.
Watch the video
Project repository
The system adopts advanced anti-detection techniques: undetected_chromedriver for stealth browsing, proxy and user-agent rotation, simulation of human interactions, spoofing of navigator properties, and overriding JavaScript methods to avoid fingerprints. It operates in headless mode with pyvirtualdisplay, creates temporary profiles, and updates libraries against anti-bot techniques.
Project repository
Project repository 2
This interactive system translates natural language questions into SQL queries using Open AI and LangChain, executes them against a SQLite database, and provides detailed answers. It features database integration, customizable prompts, and an interactive CLI for real-time querying.
Project repository
A tutorial for training a Multi-Layer Perceptron (MLP) to recognize handwritten digits from MNIST using Keras. Features data preprocessing, Keras Functional API with BatchNormalization and Dropout, TensorBoard callbacks for monitoring, Visualkeras visualization, metrics (confusion matrix, precision, recall, F1-score), and model saving/loading. Includes sample predictions and result reporting.
Watch the video
Project repository
Some Clients
I am a Senior Software Developer & AI Engineer with over 15 years of experience building production-grade software systems. My core expertise lies at the intersection of software engineering and artificial intelligence, designing scalable, robust applications that seamlessly integrate AI capabilities for real-world enterprise environments.
Certifications: I am multi-certified in AWS for cloud expertise and IBM certified for AI engineering, bringing proven credentials to every project.
AI & Machine Learning Expertise: I architect and deploy end-to-end ML solutions covering supervised, unsupervised, and reinforcement learning. My deep learning experience spans CNNs, RNNs, LSTMs, and Transformer architectures, with hands-on expertise in model training, validation, hyperparameter tuning, transfer learning, and fine-tuning for production deployment.
AI Specializations: I design sophisticated NLP systems (text processing, sentiment analysis, chatbots, language models, LLM fine-tuning), Computer Vision solutions (image classification, object detection, segmentation, image generation), hybrid RAG architectures with vector and graph databases (Pinecone, Weaviate, Chroma, Neo4j), and AI Agent systems using LangChain/LangGraph for autonomous, intelligent multi-agent workflows.
Cloud & DevOps: I specialize in deploying AI at scale on AWS (SageMaker, Bedrock, Lambda, EC2, S3, RDS). I implement robust DevOps practices including containerization (Docker, Kubernetes), automated CI/CD pipelines, production model serving, monitoring, and experiment tracking with MLflow and Weights & Biases. I ensure scalability, security, and reliability in cloud-native solutions.
Full-Stack Development: I have mastery in Python, PHP, JavaScript, Node.js, SQL, TypeScript, TensorFlow, and Keras. Beyond AI, I build fast, maintainable applications using modern frameworks like React, Next.js, Django, Flask, and Express.js. I design scalable APIs and integrate AI functionalities into production systems with proper software engineering practices.
Tools & Frameworks: My toolkit includes Hugging Face Transformers, LangChain/LangGraph for AI applications, vector databases for RAG systems, and comprehensive ML platforms for training and deployment. I emphasize clean architecture, version control, testing, and maintainable code across all projects.
I am passionate about solving complex problems with AI-driven solutions that actually work in production. Constantly exploring cutting-edge technologies, I focus on delivering enterprise-grade systems that are secure, scalable, and built for long-term success.
I offer my services as a Senior Software Developer & AI Engineer to collaborate with companies of all sizes. Whether as a full-time partner or on a project basis as a freelancer (with VAT number), I am committed to delivering robust, production-ready solutions.
If you are interested in collaboration or desire more information, please do not hesitate to contact me. I am here to help you build intelligent, scalable systems that drive real business value.
Stacks e Frameworks