Alkis Polyzotis

Neoklis (Alkis) Polyzotis is a technical lead in the machine learning platform team at Databricks. Before Databricks, he worked at Google building data/model evaluation tools for TensorFlow Extended and a catalogue for Google's internal data lake. He also held a faculty position at UC Santa Cruz. He holds a PhD in Computer Sciences from the University of Wisconsin at Madison, and an engineering diploma from the National Technical University of Athens, in Greece.

Alkis Polyzotis's posts

Building Custom LLM Judges for AI Agent Accuracy

November 4, 2025/5 min read

Building Custom LLM Judges for AI Agent Accuracy

MLflow 3.0

June 11, 2025/12 min read

MLflow 3.0: Build, Evaluate, and Deploy Generative AI with Confidence

AI Agents: Evaluation

March 12, 2025/14 min read

Introducing Enhanced Agent Evaluation

Streamline AI Agent Evaluation with New Synthetic Data Capabilities

December 9, 2024/8 min read

Streamline AI Agent Evaluation with New Synthetic Data Capabilities

Databricks announces significant improvements to the built-in LLM judges in Agent Evaluation

September 5, 2024/8 min read

Databricks announces significant improvements to the built-in LLM judges in Agent Evaluation

social card

July 2, 2024/9 min read

Announcing Mosaic AI Agent Framework and Agent Evaluation

lakehouse-monitoring-social-card

December 12, 2023/5 min read

Lakehouse Monitoring: A Unified Solution for Quality of Data and AI

October 31, 2023/8 min read

Announcing MLflow 2.8 LLM-as-a-judge metrics and Best Practices for LLM Evaluation of RAG Applications, Part 2

Announcing Inference Tables: Simplified Monitoring and Diagnostics for AI models

October 5, 2023/4 min read

Announcing Inference Tables: Simplified Monitoring and Diagnostics for AI models

Best Practices for LLM Evaluation of RAG Applications

September 12, 2023/15 min read

Best Practices for LLM Evaluation of RAG Applications