![Sebastian Schkudlara](profile_image_md.jpg) ## ๐Ÿ•น๏ธ PLAYER PROFILE | ๐ŸŽฎ CLASS | **Senior Software Architect** (Lead / Senior) | | :--- | :--- | | **ORIGIN** | **Germany ๐Ÿ‡ฉ๐Ÿ‡ช / Poland ๐Ÿ‡ต๐Ÿ‡ฑ** (Base: Germany ๐Ÿ‡ฉ๐Ÿ‡ช / Spain ๐Ÿ‡ช๐Ÿ‡ธ) | | **CONTACT** | [sebastian.schkudlara@gmail.com](mailto:sebastian.schkudlara@gmail.com) \| [LinkedIn](https://linkedin.com/in/schkudlara) \| [jevvellabs.com/cv.html](https://jevvellabs.com/cv.html) | | **INFO** | ๐ŸŽง [Audio CV](https://youtu.be/SesFjz6gWOc) \| ๐Ÿ“ž \+34 603 769 903 \| \+49 175 1288106 | | **AVAILABILITY** | Open to Remote (EU / US) \| Available Immediately | ## ๐Ÿ›ก๏ธ SKILL TREE | ๐Ÿ”ด **CORE TECH** | ๐Ÿ”ต **AI & DATA** | ๐ŸŸข **ARCHITECTURE** | | :--- | :--- | :--- | | **Ruby** (Rails), **Python**, **FastAPI** | **Agentic AI Architecture** | **Microservices** | | **PostgreSQL**, **Redis**, **TypeScript** | **Multi-Agent Orchestration** | **Event-Driven** (Kafka/RabbitMQ) | | **Node.js**, **React** | **Tool Calling & Routing**, **MCP** | **Kubernetes**, **Docker**, **AWS/GCP** | |   | **LangChain**, **PydanticAI** |   | |   | **Prompt Engineering** |   | ## โš”๏ธ SPECIAL ABILITIES - **Polyglot**: ๐Ÿ‡ฉ๐Ÿ‡ช German (Native), ๐Ÿ‡ต๐Ÿ‡ฑ Polish (Native), ๐Ÿ‡ฌ๐Ÿ‡ง English (Fluent), ๐Ÿ‡ช๐Ÿ‡ธ Spanish (Fluent). - **Hyper-Productivity**: Rapid prototyping, TDD, & deployment. - **Team Buff**: Mentorship, Team Building, & Technical Leadership. ## ๐Ÿงฐ TOOLBELT & INVENTORY > **Databases**: MongoDB, Neo4j, MySQL, SQLite, Memcached, Elasticsearch. > **DevOps & Scripting**: Bash/Shell, Ansible, Terraform, GitHub Actions, Prometheus, Grafana. > **AI Frameworks**: LangChain, LangGraph, PydanticAI, Hugging Face, OpenAI API, Anthropic API, Gemini API. > **Architecture**: REST, GraphQL, gRPC, JSON-RPC, OAuth 2.0, WebSocket. > **Blockchain** *(secondary)*: Polygon, Ethereum, Solidity, Hyperledger, Hedera, Chainlink, Stellar. --- ## PROFESSIONAL SUMMARY Senior Backend Architect turned **Agentic AI Infrastructure specialist** โ€” 19+ years building distributed systems, now designing the tools and protocols that make autonomous AI agents work in production: routing proxies, P2P agent networks, A2A communication layers, and RAG pipelines engineered for scale. ### Key Achievements: SwitchAI โ€“ Engineered a multi-model AI proxy, optimizing request routing across leading LLM providers (OpenAI, Anthropic, Google AI Studio, Mistral, Hugging Face) and custom local models, reducing AI operational costs by 30%. HiveMindAI โ€“ Built an autonomous AI agent marketplace for data analysis, content generation, and workflow automation, reducing agent deployment from weeks to days. AI-Driven Logistics (ChainGO) โ€“ Led the shift to AI-first automation in logistics, introducing AI-powered document processing and anomaly detection, reducing manual processing by ~70%. Proficient in Kubernetes, AWS/GCP, FastAPI, LangChain, PydanticAI, RAG workflows, Python-based AI frameworks, and Ruby on Rails API development to deliver robust, cost-effective, and scalable platforms. --- ## OPEN SOURCE PROJECTS ### [Scoutica Protocol](https://github.com/rschumann/scoutica-protocol) ๐Ÿ†• **Creator & Protocol Designer** | An open-source, decentralized protocol that replaces traditional CVs with AI-agent-readable "Skill Cards." Candidates publish structured JSON/YAML/Markdown profiles to their own Git repositories, making their career data globally discoverable by any AI agent without depending on centralized platforms (LinkedIn, Indeed). Features a three-zone privacy model, anti-spam micropayments (~$0.05) to block mass data scraping, and a full CLI toolchain for card generation and validation. **Tech Stack:** JSON Schema, YAML, Markdown, CLI (Node.js), Mintlify Docs | Website: [scoutica.com](https://scoutica.com) ### [switchAILocal](https://github.com/traylinx/switchAILocal) **Creator & Lead Architect** | Unified AI gateway that bridges Gemini, Claude, Ollama, and CLI tools into a single OpenAI-compatible server. Features intelligent routing, load balancing, and autonomous self-healing with Superbrain intelligence. **Tech Stack:** Go, AI Gateway, OpenAI API, LLM Routing, React UI ### [Traylinx CLI](https://github.com/traylinx/traylinx-cli) **Creator & Lead Developer** | Command-line interface for managing AI agents with conversational Cortex interface. Natural language processing, multi-turn conversations, and intelligent command execution. **Tech Stack:** Python, CLI, NLP, Agent Management, Typer ### [Traylinx Stargate](https://github.com/traylinx/traylinx-stargate) **Creator & Lead Architect** | P2P networking plugin for agent-to-agent communication. Features zero-trust identity with Ed25519, multi-transport support (NATS/libp2p), Circuit Relay v2 for NAT traversal, connection pooling, and comprehensive health monitoring. Production-ready mesh network for distributed AI agents. **Tech Stack:** Python, P2P, NATS, libp2p, NAT Traversal, Zero-Trust ### [A2A Ruby SDK](https://github.com/traylinx/a2a-ruby) **Creator & Maintainer** | Production-grade Ruby SDK for Google's Agent2Agent (A2A) Protocol. Enables seamless agent-to-agent communication via JSON-RPC 2.0, gRPC, and HTTP+JSON transports with full OAuth 2.0 support. **Tech Stack:** Ruby, A2A Protocol, gRPC, OAuth 2.0, JSON-RPC ### [2md (Agentic Data Ingestion Engine)](https://2md.traylinx.com) **Creator** | Engineered a high-fidelity HTML-to-Markdown conversion pipeline designed specifically for AI agents. Features deep site crawling, batch processing, and advanced WAF/Cloudflare bypass using stealth Puppeteer rotation. Includes a REST API for programmatic agent discovery and automatic "AI Skill Bundle" generation. **Tech Stack:** Node.js, Puppeteer, Markdown AST, Express, REST API ### [google-drive-intelligent-mcp](https://github.com/traylinx/google-drive-intelligent-mcp) **Creator** | Intelligent MCP (Model Context Protocol) server for Google Drive operations. Enables AI agents to autonomously discover, read, and manage Drive files via the standardised MCP interface. **Tech Stack:** Node.js, MCP Protocol, Google Drive API, OAuth 2.0 ### [Traylinx Authentication Clients](https://github.com/traylinx/traylinx-auth-client-py) **Creator & Maintainer** | Enterprise-grade authentication clients for Traylinx Sentinel API with full A2A Protocol support. Available for [Python](https://github.com/traylinx/traylinx-auth-client-py) and [Node.js](https://github.com/traylinx/traylinx-auth-client-js) with OAuth 2.0, JWT, and secure token management. **Tech Stack:** Python, JavaScript, OAuth 2.0, JWT, Security **Additional Projects:** [homebrew-traylinx](https://github.com/traylinx/homebrew-traylinx), [scoop-traylinx](https://github.com/traylinx/scoop-traylinx), [a2a-ruby-samples](https://github.com/traylinx/a2a-ruby-samples) **GitHub Organizations:** [@traylinx](https://github.com/traylinx) | [@rschumann](https://github.com/rschumann) --- ## CORE COMPETENCIES ### AI & Agentic Development LLM Integration: OpenAI, Anthropic, Google AI Studio, Mistral, DeepSeek, Alibaba Cloud, NVIDIA NIM, Hugging Face, open source and custom models including local models environments. RAG Pipelines: Retrieval-augmented generation for high-accuracy AI responses AI Orchestration: Agent-based automation with PydanticAI, LangChain, Hugging Face, and custom multi-agent systems. Vector Databases: Pinecone, ChromaDB, and pgvector for semantic search and AI memory. ### Microservices & DevOps Cloud & Containerization: Kubernetes, Docker, Terraform, AWS, GCP, Azure. Event-Driven Systems: Kafka, RabbitMQ, AWS SQS/SNS, Pub/Sub, Sidekiq, Shoryuken. CI/CD & Infrastructure as Code: Automated deployments with GitHub Actions, comprehensive observability (Prometheus, Grafana). ### Backend Engineering & Data API Development: FastAPI, Ruby on Rails, RESTful, GraphQL, gRPC & JSON-RPC APIs. Real-Time Data Processing: Redis, Memcached, streaming analytics. Database Expertise: PostgreSQL (with pgvector), MongoDB, Neo4j โ€“ optimized for AI and event-driven workloads. ### Leadership & Consulting Engineering Team Scaling: Agile methodologies, sprint planning, remote collaboration. AI Strategy & Consulting: AI-driven automation, business intelligence integration. MLOps & Model Lifecycle Management: Continuous retraining, performance optimization. --- ## PROFESSIONAL EXPERIENCE ### Freelance Highlights: TRAYLINX (2024 โ€“ Present) **Role:** Freelance Developer | Product Architect #### Key Projects & Achievements: ##### ๐Ÿ”น SwitchAI (Multi-Model AI Proxy) - **Architected and engineered** an AI request-routing proxy, dynamically selecting models based on cost, latency, and performance. - **Unified API integrations** across leading LLM providers (OpenAI, Anthropic, Google AI Studio, Mistral, Hugging Face) and custom local models, optimizing cost-efficiency by 30%. ##### ๐Ÿ”น Scoutica Protocol: Decentralized Career Data Protocol - **Designed and built an open-source protocol** that replaces traditional CVs with AI-agent-readable Skill Cards, enabling candidates to own and control their career data. - **Engineered the multi-agent recruitment platform** underneath, orchestrating specialized AI agents using a resilient, event-driven architecture built on AWS SNS/SQS. - **Tech Stack:** Python (FastAPI), Ruby on Rails, PostgreSQL (pgvector), JSON Schema, AWS, Docker, Kubernetes. | Website: [scoutica.com](https://scoutica.com) ##### ๐Ÿ”น HiveMindAI (AI Agent Marketplace) - **Built a marketplace** for autonomous AI agents specializing in data analysis, content generation, and multi-step workflow automation. - **Designed RAG-based systems** to reduce hallucinations and increase accuracy in complex retrieval tasks. - **Developed Traylinx CLI** for seamless agent lifecycle management and distribution. | URL: [github.com/traylinx/traylinx-cli](https://github.com/traylinx/traylinx-cli) ##### ๐Ÿ”น 2md: AI-Ready Markdown Engine - **Engineered an advanced data ingestion tool** designed to feed RAG pipelines and AI agents. - **Integrated headless Chrome, OCR, and Vision AI** to perfectly convert URLs, PDFs, and unstructured documents into clean, agent-readable Markdown and specialized "AI Skill Bundles." | Website: [2md.traylinx.com](https://2md.traylinx.com) ##### ๐Ÿ”น A2A Ruby GEM - **Developed a production-grade Ruby Gem** for Google's Agent-to-Agent (A2A) protocol, supporting JSON-RPC 2.0, gRPC, and OAuth 2.0/JWT/mTLS security layers. | URL: [github.com/traylinx/a2a-ruby](https://github.com/traylinx/a2a-ruby) ##### ๐Ÿ”น Advanced OAuth 2.0 Authentication Service - **Designed a high-security authentication microservice** supporting social logins, 2FA/OTP, and specialized A2A flows with AES-256-GCM encryption. | Clients: [Python](https://github.com/traylinx/traylinx-auth-client-py) \| [Node.js](https://github.com/traylinx/traylinx-auth-client-js) **Overall Tech Stack:** Python, Ruby, RoR, React, Docker, Kubernetes, AWS, GCP, PydanticAI, LangChain, Hugging Face, Redis, Kafka, [traylinx.com](http://traylinx.com) ### Monodon (Navantia), Madrid โ€” Deeptech AI Specialist (Jul 2023 โ€“ Apr 2025) - Architected and implemented advanced RAG (Retrieval-Augmented Generation) systems for Navantia's deeptech innovation unit, enhancing data retrieval accuracy for strategic R&D projects. - Led model fine-tuning initiatives for specialized AI applications, optimizing performance for complex, high-stakes industrial use cases. - Collaborated with cross-functional teams to integrate AI solutions into Navantia's core technology stack, driving innovation in maritime and defense sectors. Tech Stack: Python, PyTorch, Hugging Face, LangChain, RAG, Vector Databases, Kubernetes ### Babel Group, Madrid โ€” AI Engineer (Jun 2024 โ€“ Dec 2024) *(Parallel Freelance Contract)* - Developed RAG-based AI solutions, integrating with enterprise data infrastructure for high-accuracy responses. - Optimized LLM performance, reducing latency and cost with fine-tuned AI models. - Built NLP pipelines for summarization, entity extraction, and sentiment analysis, enhancing automation workflows. Tech Stack: Python, Hugging Face, LangChain, TensorFlow, Docker, Kubernetes, PostgreSQL ### ChainGO, Madrid โ€” Head of Development (Feb 2019 โ€“ Jul 2024) - **Pioneered AI-driven automation** in logistics and shipping, reducing operational inefficiencies. - **Built microservices-based document processing** ([docBlox](https://docblox.chaingotech.com/)), integrating AI & blockchain. - **Developed the eBL Platform**, digitizing the Bill of Lading process using Polygon blockchain. - **Implemented ForestChain Digital Passport**, a blockchain system for forest product traceability. **Tech Stack:** Python, Node.js, Ruby, AWS, PostgreSQL, Docker, Blockchain (Polygon), AI-driven logistics optimization. ### Agentero, San Francisco โ€” Head of Development (May 2017 โ€“ Dec 2018) - **Grew development team** from 1 to 15 engineers, establishing Kubernetes-based infrastructure and CI/CD pipelines. - **Built real-time event-driven analytics** for insurance risk analysis, delivering a scalable backend ([agentero](https://agentero.com/)). **Tech Stack:** Ruby, Python, Golang, Node.js, Kafka, AWS, GCP, Kubernetes. ### Vizzuality, Madrid โ€” Backend Engineer (May 2014 โ€“ May 2017) - **Developed environmental data APIs** for large-scale data visualization. - **Unified diverse datasets** with a microservices-based architecture, improving data accessibility globally. **Tech Stack:** Python, Ruby, Node.js, AWS, PostgreSQL. --- ## KEY PROJECTS โœ” Scoutica Protocol (Traylinx) โ€“ Open-source decentralized protocol replacing CVs with AI-readable Skill Cards โœ” SwitchAI (Traylinx) โ€“ AI routing proxy saving 30% in AI operational costs โœ” HiveMindAI (Traylinx) โ€“ Accelerated AI agent deployment from weeks to days โœ” RAG Solutions (Babel Group) โ€“ Improved AI-driven Q\&A accuracy & retrieval โœ” AI-Driven Logistics (ChainGO) โ€“ Automated shipping documentation processing --- ## FEATURED PROJECTS #### ChainGO eBL Platform - Revolutionized the Bill of Lading process by digitizing and automating documentation workflows. - Utilized Polygon blockchain to create NFT-backed eBLs, ensuring immutable ownership and traceability. - Reduced CO2 emissions and manual labor through digital documentation. - **Tech Stack:** Python, Blockchain, NFT, Ruby. | Website: [ebl.chaingotech.com](https://ebl.chaingotech.com) #### ForestChain Digital Passport - Developed a blockchain-based Digital Passport system for forest product traceability. - Enabled end-to-end transparency and compliance with sustainability standards via blockchain-backed certifications. - **Tech Stack:** Python, Blockchain, Ruby. | Websites: [forestchain.chaingotech.com](https://forestchain.chaingotech.com), [forest-chain.com](https://forest-chain.com) #### API (Microservices Architecture) for World Resources Institute - Developed backend APIs for data analysis tools as part of a global environmental initiative led by the White House OSTP and WRI. - Created scalable query services and public APIs, used by researchers and universities worldwide. - **Tech Stack:** Python, Microservices, API, Node.js. | Website: [resourcewatch.org](https://resourcewatch.org) | [api.resourcewatch.org](https://api.resourcewatch.org) #### Data Management for Red Elรฉctrica de Espaรฑa - Designed and deployed a backend system to process and serve thousands of indicators updating in real-time. - Managed Oracle Database SQL scripting and Ruby on Rails infrastructure for data visualization. | Website: [esios.ree.es](https://www.esios.ree.es) #### Language Learning Platform (Palabea) - Founded and led the development of a virtual classroom platform with video conferencing and document sharing capabilities. - Focused on user-centric design and backend architecture to create an engaging learning experience. | Website: [Palabea on Mashable](https://mashable.com/2008/05/27/palabea) --- ## EDUCATION & EXPERTISE ๐ŸŽ“ **Academic Background:** TU Berlin ๐Ÿ“š **Technical Focus & Research:** LLM fine-tuning, microservices best practices, and AI architectures --- ## ๐Ÿ“‘ Portfolio Formats This repository contains my CV in three distinct formats: 1. **[Online Interactive Edition](https://jevvellabs.com/cv.html)**: The live, high-fidelity webpage with interactive skill trees and 80s aesthetic. 2. **[Web Edition (Local Source)](index.html)**: The source HTML for the interactive CV. 3. **[Markdown Edition](Sebastian_Schkudlara_CV_2026.md)**: Clean, structured version optimized for GitHub. 4. **[PDF Edition](Sebastian_Schkudlara_CV_2026.pdf)**: Polished, printer-friendly document.