Jay Patel

About

ML/LLM engineer with production experience building a RAG-based LLM support assistant (FastAPI, Redis, Kafka) with multi-layer validation and human-in-the-loop feedback loops to improve accuracy over time. Has orchestration and MLOps depth using Airflow and Kubeflow on Kubernetes (autoscaling, alerting, monitoring) and delivered measurable ops impact (40% ticket efficiency improvement) by partnering closely with customer support teams.

Experience

Education

Key Strengths

• Built and deployed a production LLM support assistant using RAG over product docs and historical tickets
• Designed multi-layer response validation with semantic similarity scoring and human review routing to reduce hallucinations
• Implemented continuous improvement loops using user edits/satisfaction ratings with weekly retraining of retrieval/ranking models
• Production ML orchestration experience with Airflow (DAGs, dependency management, Slack/email alerts, SLA monitoring) and Kubeflow on Kubernetes (autoscaling, cost/resource optimization)
• Reliability-focused evaluation practices: modular component tests, A/B testing, shadow deployments, and Prometheus-based monitoring for drift/performance degradation
• Demonstrated business impact via NLP ticket classification collaboration with non-technical stakeholders (reported 40% improvement in ticket efficiency)