Selected Projects
The projects below represent the cumulative track record of the HubLab team and founder, including engagements delivered prior to the formal incorporation of HubLab (Astana, January 2025) and partnerships through which the team's technical expertise has been developed.
Botable.dev — AI Bot Generation Platform
LLMHubLab's own product. A business describes the job in plain language; Botable writes a Telegram agent in Python, checks that it runs and puts it live for sales and support. We already serve open-weight models with vLLM on our own NVIDIA GPUs in Astana and are moving Botable onto that stack.
Legal AI Platform — Lead Technical Expert
LLM Founder track recordLead technical expert of an AI legal assistant since March 2025, from the foundation stage. Ran contractor selection over 21 commercial proposals and accepted the MVP, released in July 2025. Sets tasks for the contractor team of 3 to 10 people. Built analytics on the production data and found the high-value user segments; the product was refocused on them, and target-segment conversion went from 5% to 17%. Engagement under NDA.
IPNote — Patent Search AI
LLM Founder track recordDeep Research agentic pipeline for a LegalTech startup. The system automates patent database analysis using a multi-agent architecture: one agent parses legal constraints, another performs semantic search across patent databases, and a coordinator synthesizes results into structured reports. Designed for patent attorneys who need comprehensive prior art research.
Agreemer — AI Contract Risk Analyzer
LLM Founder track record (2022)One of the earliest LLM-powered tools built on ChatGPT API in 2022. Users upload NDAs and contracts — the system highlights risk clauses, identifies unfair terms, flags jurisdiction mismatches, and provides a risk score. Designed for startups and freelancers who need quick legal review without hiring a lawyer. Later expanded to support multi-language contracts.
Exam Proctoring — Computer Vision System
CVReal-time computer vision system for detecting exam violations from overhead cameras. Trained two model families (YOLO and DETR) on custom-annotated datasets of prohibited objects and suspicious behavior. Includes camera distortion calibration, multi-object tracking, and a dashboard for invigilators with instant alerts. Deployed on-premise in exam centers.
MyMind — Cognitive Diagnostics via Gesture Recognition
CV Founder track recordMobile application for early screening of age-related cognitive conditions through hand gesture tracking. Integrated Google MediaPipe for real-time hand landmark detection with a custom ML classifier trained on 7,000+ annotated gesture images. The project won “Best Social Impact” at Astana Hub Battle 2023; Ivan worked on it as the ML developer.
SpaceVela — CV for Additive Manufacturing in Space
CV Founder track recordComputer vision defect segmentation model for quality control in 3D printing of spacecraft structural components. Managed two employees: data labelling and printer control software. The startup was accepted into the Creative Destruction Lab (CDL) Space Stream at the University of Toronto — one of the top space-tech accelerators globally. Model deployed on-premise directly on the manufacturing device.
RAG System for Logistics Company
LLM Team prior workEnterprise chatbot built on Retrieval-Augmented Generation for a freight transportation company. Documents are chunked, embedded into vectors, and stored in a vector database. Employees type natural language questions and receive precise answers with source references. Reduced average document lookup time and improved onboarding speed for new staff.
Hotel Sales Bot — AI Assistant
Chatbot Team prior workTelegram-based AI sales assistant for a hotel chain. Built custom parsers for three major hotel aggregator platforms (Booking, Agoda, Hotels.com) to provide real-time price comparisons. The bot handles inquiries 24/7, suggesting rooms, answering FAQ, and routing qualified leads to human managers. International remote team, solo backend development.
School Network Data Platform (POC)
Data Team prior workProof of Concept analytics platform for a school network. Combines RAG for qualitative queries with Text-to-SQL for quantitative questions. Teachers and administrators type questions like «average attendance last month» and the system automatically generates SQL queries, retrieves data, and presents visualized answers. Hybrid AI approach handling both structured and unstructured school data.
Thermal Image Augmentation
CV Founder research (ITMO)Published research on a novel data augmentation method for thermal imaging. Developed a technique that mimics visible-spectrum characteristics in infrared images to improve object detection for autonomous driving. Achieved ~13% improvement in prediction accuracy over baseline models. Research conducted and published at ITMO University, trained on PyTorch with custom augmentation pipelines.
