I am a Machine Learning Architect and Lead Software Engineer with over 14 years of experience in artificial intelligence, machine learning, and cloud-based distributed systems. Over the past three years, a significant portion of my work has focused on Generative AI, Large Language Models (LLMs), and agentic AI architectures, building production-grade systems that leverage AI to automate processes, enhance data analysis, and power intelligent applications.
Currently, I work as a Lead Software Engineer and Machine Learning Architect at EPAM, where I design and lead the implementation of end-to-end AI systems. My experience spans the full AI/ML lifecycle, including data engineering, feature engineering, model training, deployment, monitoring, and operationalization through MLOps and LLMOps practices.
In recent years, I have actively worked on Generative AI projects, including:
Designing and implementing RAG (Retrieval-Augmented Generation) architectures for semantic search platforms, enterprise knowledge systems, and intelligent assistants.
Fine-tuning and adapting Large Language Models for domain-specific business applications.
Building agentic workflows and AI agents, leveraging modern AI orchestration frameworks and event-driven architectures.
Developing production LLM pipelines, integrating embeddings, vector databases, and retrieval systems.
Creating applications powered by LLMs, prompt engineering, and multi-agent orchestration.
I also have strong experience designing cloud-native AI architectures, leveraging AWS, Infrastructure as Code (AWS CDK), scalable data pipelines, and real-time processing systems.
My background in machine learning, system architecture, backend engineering, and cloud computing enables me to design and deploy robust, scalable, production-ready AI platforms that deliver measurable business value.More...