Dmitry Ivanov | ML Engineer & MLOps

Dmitry Ivanov | ML / AI Engineer · MLOps Portfolio Dmitry Ivanov ML / AI Engineer · MLOps 14+ years in simulation engineering and HPC (CFD/DEM, computational workflows, team leadership). Production ML evidence via Chemwatch, SoccerPredictAI (MLOps), and CAE Copilot (Applied AI in CAE); currently Head of Simulation Modeling Bureau at Rostselmash. Engineering Impact at a Glance 950K+ Data points ingested & processed in end-to-end ML pipelines 12x Speedup in computational workflows via Python automation 95% Reduction in manual data extraction (OCR+NLP pipeline) 2 → 10 Engineers built, mentored, and led in HPC teams Location Remote · Open to EU relocation Phone+375 (29) 155-69-01 Links linkedin.com/in/dmitry-ivanov-ds· gitlab.com/dmitry-ivanov-ds Email damiyan.ivanov@gmail.com Featured Projects SoccerPredictAI – Production ML & MLOps Platform May 2025 – May 2026 SoccerPredictAI· Full project details· Docs (evidence) - Automated data ingestion for 950,000+ football matches across 26 years of history from 3 heterogeneous sources (Selenium/Selenoid, Chrome DevTools Protocol XHR interception, REST batch). - End-to-end MLOps: DVC for data versioning, Great Expectations for strict data contracts, and MLflow for experiment tracking with nested Optuna trials. - Leakage-safe experiment framework: walk-forward CV across 6 data fractions × 5 models (30 MLflow nested runs); XGBoost selected via CV logloss only — no holdout peeking - Tuned XGBoost hyperparameters via Optuna (100 trials, CV-only objective); holdout evaluated exactly once in dedicated final_train stage, preventing selection bias - Dual inference API: sync FastAPI endpoint (<500ms p95) + async batch precompute via Celery/RabbitMQ — decouples prediction freshness from request latency - Deployed on Kubernetes + Helm; Prometheus + Grafana monitoring; DVC pipeline versioning (all stages hashed for reproducibility) - End-to-end CI/CD: GitLab CI (ruff lint + pytest), SOPS + Age secrets, Grea