Yeshwanth Pulapa

About

ML/LLM engineer building production, real-time fraud detection for financial transactions using a two-tier architecture (fast ML + GPT) to deliver both low-latency decisions and analyst-friendly risk explanations. Experienced orchestrating end-to-end retraining, drift monitoring, and automated model promotion with Databricks Jobs/Workflows and MLflow, and partnering closely with fraud analysts to tune alerts, thresholds, and dashboards.

Key Strengths

• Built and deployed production LLM systems for real-time fraud detection in financial transactions
• Designs low-latency architectures combining fast ML models with LLMs for contextual explanations
• Implements continuous retraining pipelines with automated evaluation and promotion to serving endpoints (Databricks + MLflow)
• Strong monitoring and reliability practices: latency/performance tracking, drift detection, alerting, regression testing
• Systematic debugging via ablation tests, logs, controlled experiments, and iterative prompt/data refinement
• Effective collaboration with non-technical fraud analysts to translate model outputs into actionable risk explanations and workflows

Experience

Education

Skills

Languages