Looking for a job

Patrick Mitchell

@patrickmitchell

Message

Senior AI Engineer building production GenAI, RAG pipelines, and cloud-native ML infrastructure.

United States

Message

What I'm looking for

I’m looking to build and scale production GenAI systems—RAG, agent workflows, and LLMOps—on cloud-native backends, with strong observability, responsible AI governance, and continuous delivery that improves reliability and cost/performance.

I’m a Senior AI Engineer who builds production AI platforms, distributed systems, and cloud-native ML infrastructure, with deep specialization in Generative AI, RAG pipelines, and LLMOps. At Chewy, I architected production-grade RAG and LangGraph agent workflows with OpenAI/Claude integrations, shipping AI-assisted support and telehealth experiences across healthcare platforms.

I also lead end-to-end engineering for reliable, scalable systems—delivering an AI forecasting and fulfillment optimization platform and an enterprise LLMOps framework with prompt versioning, hallucination detection, evaluation pipelines, guardrails, human-in-the-loop review, and CI/CD automation. Earlier, I built Disney+ personalization and recommendation infrastructure at scale and developed backend infrastructure for Apple Pay on the Web and other mission-critical services, with a strong focus on observability, reliability, and responsible AI governance.

Experience

Work history, roles, and key accomplishments

Current

Software Engineer III (AI/ML)

Current

Chewy

Apr 2022 - Present (4 years 2 months)

Architected production-grade RAG and LangGraph agent workflows for Chewy Connect with a Vet™, integrating OpenAI/Claude APIs and FastAPI microservices to improve enterprise support and telehealth experiences. Built an AI forecasting and fulfillment optimization platform that improved inventory forecast accuracy by 18% and reduced fulfillment latency by 22%, and delivered 99.99% availability for lo

RAG LangGraph LLMOps OpenAI API fastAPI AWS Sagemaker Kubernetes Kafka PyTorch OpenSearch

AI/ML Engineer

The Walt Disney Company

Nov 2018 - Mar 2022 (3 years 4 months)

Built Disney+ personalization and recommendation systems using real-time behavioral streaming, TensorFlow, Spark, and Kafka, supporting growth beyond 100M subscribers and increasing engagement and watch time. Developed content search and metadata intelligence with BERT embeddings and transformer-based ranking, and implemented ML pipelines, monitoring, and MLOps/CI/CD to improve production model re

TensorFlow Spark Kafka Kubernetes BERT OpenSearch MLOps Airflow Real Time Streaming Data

Software Engineer

Apple

Jun 2016 - Sep 2018 (2 years 3 months)

Developed scalable backend infrastructure for Apple Pay on the Web and iMessage App Store/group FaceTime services, supporting hundreds of millions of devices with strict low-latency and reliability requirements. Built event-driven microservices and secure payment workflows (tokenization, request signing, fraud prevention, and replay protection) and implemented iCloud Drive/iOS Files synchronizatio