Asrith Velireddy

About

ML/LLM engineer at Adobe who deployed a transformer-based personalization and campaign-targeting recommender system end-to-end, including PySpark/Airflow pipelines processing 12M+ events/day and containerized inference on AWS SageMaker (Docker/Kubernetes). Also has hands-on LLM workflow experience (RAG, semantic search, prompt optimization, hallucination mitigation) with a metrics-driven approach to reliability, drift monitoring, and reproducible retraining via MLflow.

Experience

Education

Key Strengths

• Built and deployed transformer-based recommendation system in production at Adobe
• Scaled data pipelines to process 12M+ behavioral events/day
• Production-grade MLOps: containerized inference on AWS SageMaker with Docker/Kubernetes
• Model drift strategy: monitoring dashboards, baseline comparisons, data validation, controlled retraining
• Experiment-driven iteration using MLflow for reproducible model versioning and deployment
• Designed measurable evaluation frameworks for LLM/RAG workflows (success rate, relevance, latency, hallucination rate)
• Cross-functional communication: translated marketing/product goals into ML metrics and dashboards