Hire the Best Machine Learning Engineers
in Croatia

I help teams ship useful AI, and teach their people to use it confidently. I’m an AI educator and consultant with five years of experience in EdTech creating courses and learning programs for Fortune 500 companies. My focus areas include NLP, Computer Vision, Time Series & anomaly detection, Edge AI, and Agentic AI. What I do: • AI enablement & advisory: clarify the problem, choose the right approach/tools, and outline a pragmatic roadmap. • Course & training creation: curricula, micro-lessons, labs, projects, assessments, and facilitator guides tailored to your audience. • Technical writing: tutorials, playbooks, articles, and documentation that are accurate, readable, and SEO-sound. • Prototyping & analysis: decision-ready notebooks, lightweight demos, and visuals that de-risk bigger builds. Deliverables Complete curricula (outcomes → syllabus → lessons/modules → slides → scripts → Jupyter/Colab labs → datasets → rubrics → quizzes/exams → projects/capstones); hands-on workshops; executive briefs; technical articles; lightweight AI prototypes

⭐ CEO of Private Synapse AI ⭐ Expert for Agentic AI and AWS ⭐ 8+ Years Experience Over the years, I have worked across the full AI lifecycle; from leading AI research and development teams, to designing AI products, systems, and infrastructure, to advising CEOs on AI strategy. Today, I help companies harness the full potential of agentic AI. Projects: 🔵 AI Assistant on files Designed and shipped an AI assistant for automating knowledge work over a company's own documents. Searches the user's files, reasons over what it finds, answers with grounded citations, and generates polished PDF reports. The underlying agent framework supports streaming, persistent multi-turn sessions, semantic and full-document retrieval across PDFs, images, audio transcripts, and tables, real-time web search, sub-agents for structured-data lookups, and per-user permission scoping. (LangGraph, LangChain, DeepAgents, OpenAI, Gemini, Anthropic, AWS Bedrock, AWS AgentCore, Terraform, PostgreSQL, LangSmith.) 🔵 Generative AI OCR Researched and shipped a VLM-based OCR pipeline that captures not just raw text but also document context and structure. Reached state-of-the-art accuracy in production on cases where traditional OCR fails: notoriously difficult scripts (Thai, Japanese) and complex layouts (long tables, checkboxes, stamps). (LangGraph, LangChain, DeepAgents, vLLM) 🔵 Agentic Form Filling Built an end-to-end system that maps extracted document content into user-defined templates, turning unstructured documents into clean structured records that downstream systems can consume deterministically. Solved hard sub-problems around retrieval, multi-page table parsing, and scaling extraction to 1000+ page documents. (Python, LangGraph, Langchain, AI)) 🔵 End-to-end fully private AI speech recognition Developed an End2End speech recognition solution for transcribing speech with propriatery state-of-the-art speaker recognition (diarization) that is 10x realtime, <0.05$ per hour transcribed and is one-click deployable completely privately on AWS with TerraForm. 🟠 Enterprise-grade AWS Data Mesh Designed and deployed a multi-region multi-environment AWS Lake Formation Data Mesh solution in pure Terraform. Data Mesh operated over multiple AWS accounts representing data producers, consumers, and central data governance. It supported Lake Formation tag-based data classification with a self-serve mechanism for data onboarding and sharing. (AWS, Lake Formation, Terraform) 🔵 Call center AI Quality Control Leading efforts for developing a generative AI-based quality control solution. Training and deploying an AI pipeline that answers questions about audio call recordings by converting speech to text with a speech recognition model, diarizing speakers, and performing retrieval augmented generation with LLMs. Final scoring model is used to offer a numeric overview of quality. (Python, Pytorch, Hugging Face, Nvidia Nemo, AWS, W&B, Streamlit) 🟠 AWS Data Platform Developing an AWS multi-region data platform supporting multiple products. Developed and deployed Terraform modules for VPC, Pet EC2 instances, S3, RDS, SNS monitoring, Encryption, Log manager, System manager, Lambda, Backup, IAM SSO, and Glue. (AWS, Azure, TerraForm, Terragrunt, Azure DevOps) 🟠 AWS Hospital Migration and Landing zone Built an AWS landing zone and supporting migration from on-prem. Migrating EU Hospital to have all of their infrastructure on the cloud. Developing Terrafrom modules for VPC, Pet EC2 instances, S3, RDS, SNS monitoring, and Encryption. (AWS, Python, Terraform, Github Actions) ⚫ One-shot lip-based biometric authentication, publication, ISSN 0262-8856 🔵 Automatic Speech Recognition solution Developed and deployed an E2E custom speech recognition solution on AWS based on the Whisper architecture. Supported voice-activity-detection and speaker diarization. Model inference optimization and dockerization. Blue-green deployment and autoscaling configuration (Python, PyTorch, Docker, EC2, ECS) ⚫ From scratch implementation of Transformer (200+ stars) Implementation of Vaswani, Ashish, et al. "Attention is all you need." Advances in neural information processing systems. 2017. ⚫ Parking Occupancy Detection using Computer Vision, publication, ISSN 0957-4174 🔵 Text-based sentiment analyzer Developed a text-based sentiment and foul language detector. Utilized the FastText architecture and dockerized the solution along with FastAPI. (Python, PyTorch, Docker, FastAPI, W&B) 🔵 Natural-prosody text-to-speech model Researching and testing existing test-to-speech methods and models. Designing the data collection process and labeling guide. Performing voice-cloning by training/fine-tuning a text-to-speech model on a proprietary dataset for the purpose of voiceover generation. Packaging the solution. (Python, PyTorch, Docker, Triton Inference Server, Prodigy, AWS)

ABOUT ME MD + PhD (medical ML) and a recent MSc in AI. I work hands-on as an ML/AI engineer, mostly on healthcare AI and LLM-native apps (RAG + agents + tool/function calling), and I’m comfortable taking things from idea → prototype → production. In the last couple of years I’ve been building and shipping: - LLM-native SaaS for customer support (text + voice agents): RAG with LlamaIndex/LangChain, dynamic function calling, and parallel tool execution for faster inference, plus backend-heavy full-stack work. - Cloud deployment & maintenance on AWS + GCP (Lambda/Cloud Functions, API Gateway, Postgres, etc.). - Voice-to-voice agents using LiveKit/Twillio and LLM APIs (OpenAI / Gemini). - Research and applied projects around clinical decision support, error checking, and safety with modern LLMs/LRMs. Recently, I’ve also worked on research projects using supervised fine-tuning (SFT) and RLVR with medgemma27n and GPT-OSS, focused on medical error checking and improving patient outcomes. Working freelance on: AI in healthcare / medical AI (classical ML + deep learning) RAG applications / RAG chatbots (LlamaIndex, LangChain, vector DBs, evaluation) AI agents (LangChain, LlamaIndex, Autogen) + tool/function calling Fine-tuning (SFT, preference/RLVR-style training), dataset curation, eval & guardrails AWS Lambda + API Gateway / GCP Cloud Functions deployment End-to-end ML pipelines (data → model → monitoring) Data analysis, statistics, biostatistics, visualization Academic & medical writing, literature reviews, consulting If you message me, the fastest way to start is: what’s the goal, what data you have (and where it lives), and how the output will be used (internal tool, customer-facing app, research paper, etc.). I’m happy to jump in either as “build the thing” or “fix/upgrade what’s already there.”

🎓 8+ Years of Delivering Exceptional Value with NLP, LLM, and Chatbot Technology ⭐ Expert-Vetted - part of top 1% experts on Upwork "𝗧𝗵𝗶𝗻𝗸𝗶𝗻𝗴 𝘆𝗼𝘂'𝗿𝗲 𝗹𝗮𝘁𝗲 𝘁𝗼 𝗔𝗜 𝘁𝗼𝗱𝗮𝘆 𝗶𝘀 𝗹𝗶𝗸𝗲 𝘁𝗵𝗶𝗻𝗸𝗶𝗻𝗴 𝘆𝗼𝘂'𝗿𝗲 𝗹𝗮𝘁𝗲 𝘁𝗼 𝘁𝗵𝗲 𝗜𝗻𝘁𝗲𝗿𝗻𝗲𝘁 𝗶𝗻 𝟭𝟵𝟵𝟲." ☎️ Get the Right AI Solution for Your Needs - Let's work together to pinpoint exactly what you need with a FREE 15-minute consultation. Hi there! 👋 I'm Ivan, and I’m here to help you navigate AI with clarity and purpose. I make sure you only implement technology when it truly adds value, solving real problems rather than adding complexity. 𝗪𝗵𝘆 𝗪𝗼𝗿𝗸 𝗪𝗶𝘁𝗵 𝗠𝗲? ✅ Expertise in Solving Real Problems: With over six years of experience in this new field, I've tackled complex projects across various industries. I design solutions that are scalable, secure, and efficient. Nothing is considered impossible without thorough exploration. ✅ Fast and Efficient Delivery: I understand the importance of deadlines and budgets. My streamlined process, including timelines and regular demos, ensures you’re always informed and projects are delivered bug-free and on time. ✅ Clear Communication: I prioritize transparent communication, actively listening and asking the right questions to fully understand your needs. You’ll always be in the loop with regular updates. ✅ Added Value Beyond Development: I look for opportunities to add value, whether through pre-built solutions or custom features tailored to your business. My goal is to maximize efficiency and deliver results that matter. ✅ Long-term Partnership: I’m committed to your success, offering ongoing support and maintenance as your business evolves. I stand by my work and remain available to assist, even years down the line. 𝗜𝗻𝗱𝘂𝘀𝘁𝗿𝘆-𝗦𝗽𝗲𝗰𝗶𝗳𝗶𝗰 𝗨𝘀𝗲 𝗔𝗜 𝗖𝗮𝘀𝗲𝘀 𝗜 𝗛𝗮𝘃𝗲 𝗪𝗼𝗿𝗸𝗲𝗱 𝗢𝗻: 🤝 Recruitment: - AI Recruitment Copilot: Accelerated hiring with smarter candidate matching. - CV Parser: Reduced manual effort by automating candidate information extraction. - Job Description Parser: Streamlined job postings with accurate, AI-generated descriptions. - Candidate Ranking Systems: Improved candidate selection by prioritizing the best fits. 🏥 Healthcare: - Health Regulations Compliance Analysis: Minimized compliance risks through automated analysis. - Health Recommendation Chatbots: Enhanced patient engagement with personalized AI-driven advice. 💼 Sales: - Customer Review Analysis Tool: Unlocked insights from reviews to boost product satisfaction. - SWOT Analysis: Informed strategic decisions with AI-driven analysis. - Customer Persona Builder: Increased marketing effectiveness with detailed customer profiles. 📈 Marketing: - Social Media Post Generator: Saved time and increased engagement with automated content creation. - Thumbnail Analysis: Boosted click-through rates by optimizing visual content. - Blog Generator: Streamlined content creation with automated, high-quality posts. 📊 Business Intelligence (BI): - Document Processing with OCR and VLM: Improved document management with automated classification. - Data Structuring and Formatting: Enabled faster, data-driven decisions with structured insights. ⚖️ Legal: - Legal Document Analysis: Increased compliance and reduced errors with automated document structuring. - Similar Document Recommendations: Accelerated legal research with AI-suggested related documents. - Linking Legal Documents with Regulations: Ensured regulatory alignment, reducing compliance risks. - FTC Compliance Analysis Tool: Protected businesses from legal issues with automated content reviews. 𝗧𝗲𝗰𝗵 𝗦𝘁𝗮𝗰𝗸: - Programming Languages 🐍: Python, R - Machine Learning 🤖: Tensorflow, Keras, PyTorch - LLM 📝: HuggingFace, Mixtral, GPT-4o, LLama, Groq, Claude - Chatbot tools 💬: LangChain, RAG, LlamaIndex - Deployment 🚀: FastAPI, Streamlit, Flask, LangServe - Vectorstores 🔢: Qdrant, Pinecone, Elasticsearch - Version Control 🗃️: Git, Docker, LangSmith - Cloud Platforms 📊: Azure, AWS, GCP, Heroku 𝗦𝗲𝗿𝘃𝗶𝗰𝗲𝘀 𝗜 𝗢𝗳𝗳𝗲𝗿: - First MVP in 2 Weeks: Get a functional MVP quickly to validate your idea. - AI Strategy Planning: Develop a clear roadmap for implementing AI in your business. - Solutions Proposal: Tailored solutions to meet your specific business needs. - End-to-End Development: From ideation to deployment, I manage the full project lifecycle. - Ongoing Support and Maintenance: Continuous support to ensure your AI systems evolve with your business. - Access to DevOps Experts: Fast-track your project with my network of "plug-and-play" developers, especially if speed is a priority. Thank you for considering me for your project. Hope we can work together. 🤗 Ivan

I am a data scientist with experience in building machine learning systems, testing and deploying to production. Proficient in Linux, also experienced in building websites and scaling appropriately. - Extensive experience in building and optimizing machine learning models using Python. - Setting up CI/CD/CT environments for model validation, building and deployment. - API development using Flask and FastAPI - Proficient in comprehensive data analysis, extracting valuable insights. - Skilled in testing and deploying models to production. - Expertise in creating visually appealing and responsive interfaces. - Strong database integration and back-end development skills. - Proficient in containerization and orchestration tools like Docker and Kubernetes. - Experienced in AWS and GCP deployment. Worked in both non-agile and agile teams, always willing to share knowledge and always open to communication and help.

I am experienced Machine Learning Engineer with additional skiils in C++. I always try to meet client requirements and get expected result