Skip to main content
Paul UserPU
Open to opportunities

Paul User

@pauluser21

I build production Generative AI and GPU inference systems that improve quality, latency, reliability, and cost.

United States
Message

I've built production Generative AI systems at AWS and GPU-accelerated inference platforms at NVIDIA, improving model quality, latency, reliability, and cost across enterprise AI workloads.

At AWS, I productionized a RAG-based knowledge assistant using Amazon Bedrock, Knowledge Bases, Titan Embeddings, S3, and OpenSearch Serverless. By tuning chunking, metadata filtering, retrieval, and prompt context, I improved grounded-answer accuracy from 78% to 89% across 2,500 queries and reduced p95 retrieval latency by 30%.

I also built reusable foundation-model evaluation pipelines, reducing experiment turnaround by 60%, and introduced Guardrails, prompt management, regression testing, prompt caching, and intelligent prompt routing to reduce unsafe responses by 40%, regressions by 55%, and inference cost by 28%.

Before AWS, I worked at NVIDIA on CUDA/C++ and TensorRT inference systems, cutting end-to-end latency by 28%, improving throughput 2.3x through FP16/INT8 deployment, and delivering real-time perception workloads under 30 ms per frame. I've mentored 12 engineers on RAG architecture, prompt engineering, LLM evaluation, and production debugging.

Experience

Work history, roles, and key accomplishments

AS

Senior Machine Learning Engineer, AWS Generative AI

Oct 2019 - Jun 2026 (6 years 8 months)

Built enterprise GenAI systems on AWS Generative AI and Amazon Bedrock, focusing on RAG-based knowledge assistants, foundation-model evaluation, retrieval quality, responsible AI controls, and inference optimization. Improved grounded-answer accuracy from 78% to 89%, reduced p95 retrieval latency by 30%, and cut inference costs by 28% through prompt caching and routing.

Education

Degrees, certifications, and relevant coursework

University of Michigan logoUM

University of Michigan

Bachelor of Science, Computer Science

2012 - 2015

Bachelor's Degree in Computer Science from the University of Michigan from 2012 to 2015.

Get matched with your dream remote job

Sign up now and join over 250,000+ remote workers who receive personalized job alerts, curated job matches, and more for free!

Sign up
Himalayas profile for an example user named Frankie Sullivan