Zhyrgalbek Kalykov
Projects
Pretalk: Multi-Modal AI Voice Assistant
A multi-modal AI voice assistant that enhances voice models with speaker diarization, background noise detection, speech-to-text via OpenAI Whisper, and text-to-speech synthesis. Includes RAG-based retrieval for intelligent responses and context-aware embeddings.
UNIVERSITY AI - AskNAU
Developed an AI Q&A model using NLP and machine learning with Python, helping students at North American University get real-time answers to queries. Built the front-end using React and styled with Tailwind CSS for seamless user interaction. Optimized the model with NAU-specific data to improve response accuracy and relevance.
Work Experience
Data Engineer Intern @AiKYNETIX
Feb 2024 – Dec 2024 · Remote
Built a computer vision model to detect and count human jumps using PyTorch, OpenCV, ViTPose, and MediaPipe. Developed an AI-powered recommendation system leveraging NLP and deep learning APIs to enhance user engagement. Increased foot movement model accuracy by 70% through optimized preprocessing. Processed over 10GB of structured data for internal tooling and business insights. Debugged video-based model failures by analyzing edge cases. Collaborated with engineers and data scientists to improve real-time AI applications.
Education
North American University
Bachelor of Science in Computer Science
Studying core topics in Software Engineering, Artificial Intelligence, and Data Structures. Actively involved in AI projects and hackathons.