Christopher Gong

About Christopher Gong

Learning about AI/ ML through improving infrastructure by finding robust methods to serve models at scale and creating new data sourcing pipelines to bolster vector search to improve model and product performance.Alumni of UCI and Harker

Experience

1. Software Engineer Ii

   Hive

   Aug 2024 — Present · San Francisco, CA, US

   AI/ML Infrastructure Engineer | Distributed Inference & Vector Search at PB ScaleDesigned and operate ingestion and inference pipelines powering 100B+ vector databases, reducing batch ingestion latency from 12+ hours to under 30 minutes. Architected multi-product vector ingestion frameworks, distributed lifecycle management systems, and service discovery for dynamically routed vector databases.Contribute to GPU fleet autoscaling infrastructure using queue and inference latency metrics to optimize utilization and maintain low-latency model serving. Optimized large-scale media processing and inference data flows to improve throughput across production ML systems.Technologies & Languages: Nvidia Triton, Consul, Qdrant Vector DB (HNSW), In House KNN Vector DB, Nomad, Marathon/Mesos, Jenkins, Docker, AMQP, Github, FFmpeg, Linux/Bash, Rust, TypeScript/JSSkills: Rust, Vector Databases, AI/ML Inference Infrastructure, GPU Fleet Infrastructure, Systems Design, On-Call / Production Operations

Education

• UC Irvine

  Bachelor's degree, Computer Science

  2019 — 2023

Skills

• English
• Teamwork
• Event Planning
• Management
• Microsoft Word
• Java
• Microsoft Office
• Leadership
• Customer Service
• Research
• Microsoft Excel
• Powerpoint
• Project Management
• Marketing
• Training
• Public Speaking
• Strategic Planning
• Social Media
• C++