Kvochkin Vladyslav

Built an AI coaching platform combining long-term user memory, RAG-based personalization, structured coaching sessions, and challenge-cycle orchestration. Implemented a 6-layer memory pipeline from raw conversation data into atomic claims and rolled-up summaries, using PostgreSQL, pgvector, and embeddings. Developed LangGraph/LangChain orchestration with async memory processing, structured Pydantic outputs, and cost-aware model routing, including human-in-the-loop workflows with confirmation gates, token-budgeted context assembly, and audit trails. Created LLM evaluation workflows using golden datasets, RAG quality metrics, LLM-as-judge checks, and Langfuse traces for quality/cost monitoring.

Supported a German-language Discrete Mathematics course (84 students), gained Swiss work experience in a high-standard academic environment, and demonstrated adaptability.

Developed ML components for two retail analytics platforms processing high-frequency transactional data across 50+ US store networks. Built forecasting and anomaly detection models in Python, scikit-learn, PyTorch, and Java using statistical testing and KPI-based evaluation. Designed data pipelines and optimized MySQL schemas to reduce dashboard query latency from multi-seconds to sub-seconds. Containerized ML services with Docker and deployed on AWS in collaboration with engineering teams. Developed AI PoCs including TensorFlow Lite for lightweight computer vision deployment and PyTorch-based NLP text classification.