Pratik Jaiswal

About

ML engineer/data scientist with M&T Bank experience who built a production reinforcement-learning portfolio analytics tool for wealth management, emphasizing near real-time performance via batch/serving separation and robust generalization through stress-scenario backtesting and RL regularization. Strong MLOps background (Airflow, Grafana, MLflow) and proven ability to drive adoption with non-technical stakeholders using KPI alignment and SHAP-based explanations.

Experience

Education

Key Strengths

• Built and deployed an RL-based portfolio analytics system for wealth management in production
• Designed low-latency ML architecture by separating batch computation from lightweight serving
• Strong generalization/robustness approach for RL (entropy regularization, randomized trajectories, synthetic perturbations, stress-scenario backtesting)
• Production ML orchestration expertise with Airflow (DAGs for ingestion, feature engineering, training, evaluation, retraining, deployment)
• Operational reliability/observability focus (retries, SLAs, on-failure callbacks, structured alerts; pipeline health monitoring with Grafana)
• Rigorous evaluation methodology for time-series ML (walk-forward validation, edge-case and stress testing)
• Experiment tracking and comparability across runs using MLflow
• Effective collaboration with non-technical stakeholders; translated RL outputs into business KPIs and used SHAP dashboards to drive adoption