Data Engineer

На данный момент Data Engineer.

Мои компетенции и опыт

💼 Professional Summary

Over the past 3–5 years, I’ve led and delivered multiple AI-powered data engineering and analytics projects across finance, SaaS, and enterprise domains — specializing in LLM integration, data pipelines, and real-time insights automation. My recent work focuses on bridging machine learning systems, vector databases, and cloud-native orchestration to enable data-driven decision-making at scale.

🧠 Key Responsibilities & Achievements

• Data Pipeline Architecture & Orchestration:
Designed and deployed end-to-end ETL/ELT workflows using Python, SQL, and Prefect/Airflow, processing millions of records daily with 99.9% uptime.
Reduced manual reporting time by 40% through full pipeline automation and CI-based monitoring.

• LLM & AI Integration:
Built LLM-powered semantic search, summarization, and data retrieval systems using OpenAI, Claude, and Gemini APIs.
Implemented structured output parsing, prompt optimization, and retrieval-augmented generation (RAG) workflows for internal analytics tools.

• Machine Learning & Predictive Modeling:
Delivered production-ready loan default prediction and churn detection models, achieving 85% AUC and supporting retention campaigns that lowered attrition by 15%.
Integrated these models with APIs and BI dashboards for real-time decision support.

• Cloud & Cost Optimization:
Deployed data platforms on AWS and GCP, introducing query tuning and compression techniques that cut compute/storage costs by 20%.
Migrated legacy workloads to cloud-native data warehouses (ClickHouse, BigQuery) to boost scalability.

• Business Intelligence & KPI Dashboards:
Created executive-level dashboards with Power BI and Tableau, visualizing loan performance, customer trends, and operational KPIs.
Enabled leadership teams to monitor risk, portfolio health, and engagement metrics in real time.

• Cross-Functional Collaboration:
Partnered with PMs, data scientists, and developers to integrate analytics features into client products, aligning AI capabilities with core business goals.
Practiced Agile methodologies for sprint planning, A/B testing, and iterative delivery.

⚙️ Core Stack & Specializations

Python (Pandas, NumPy, PyTorch, Scikit-learn, FastAPI) • SQL • dbt • Prefect • Airflow
ClickHouse • BigQuery • PostgreSQL • Pinecone • Weaviate • FAISS
Power BI • Tableau • AWS • GCP • LLM APIs (OpenAI, Claude, Gemini)