Samuel Herman

About Samuel Herman

Transforming how the world searches and processes data at petabyte scaleI\'m a distinguished engineer and researcher specializing in vector search, distributed systems, and high-performance data infrastructure. With 10+ years of experience architecting solutions that process petabytes of data daily, I\'m passionate about pushing the boundaries of what\'s possible in search technology.CURRENT FOCUS:Leading search innovation at DataStax, where I\'m driving the next generation of vector search through my core contributions to the jVector library and OpenSearch ecosystem. As an OpenSearch Leadership Committee member, I help shape the technical roadmap for one of the world\'s largest open source search platforms.WHAT I DO:• Vector Search Innovation: Core contributor to jVector library, developing cutting-edge algorithms for large-scale vector indexing and retrieval• Distributed Systems Architecture: Designed petabyte-scale systems at Oracle Cloud Infrastructure and AWS that serve millions of users globally • Performance Optimization: Achieved 10x performance improvements and sub-second query times across massive datasets• Open Source Leadership: Maintaining critical infrastructure used by thousands of developers worldwideNOTABLE ACHIEVEMENTS:• Architected OCI Search Service processing petabytes of real-time data across millions of cores• Built AWS EBS analytics platform that became the template for other core AWS services• Hold multiple patents in distributed backup systems and multi-tenant encryption technologies• Speaker at OpenSearchCon 2023 & 2024 & 2025, sharing insights on core storage extensionsTECHNICAL EXPERTISE:Vector Search | OpenSearch/Elasticsearch | Distributed Systems | Machine Learning Infrastructure | Java/C++| Kubernetes | Real-time AnalyticsI regularly share insights on vector search optimization, GPU acceleration techniques, and distributed systems architecture through my technical blog. Open to discussing collaboration opportunities, technical advisory roles, and speaking engagements.

Experience

1. Architect and Researcher - Ai, Vector

   Oracle

   Jan 2026 — Present · Seattle, WA, US

Education

• Coursera.org

  Graduate extra curriculum, Computer Science

  2013 — 2015

• Bar-Ilan University

  B.Sc, Biophysics - Physics, Chemistry, Biochemistry

  2006 — 2009

• The Open University of Israel

  Computer Science Program, Computer Sciences

  2010 — 2014

Skills

• Linux
• Cloud Computing
• Python
• Databases
• Apache
• Perl
• Mysql
• Sql
• Java
• Ruby
• Nagios
• Puppet
• Chef
• Servers
• C#
• Splunk
• Ossec
• Idp
• Dns
• C++
• Distributed Databases
• Redis
• Postgresql
• Powershell
• Android Development
• Mobile Architecture
• Apache Spark