Senior AI Memory Architect for Multi-Agent Systems

EY; New Brunswick (NJ); Hybrid; USD 126,000 - 230,000; Full time

Benefits offered by this job

Hybrid work model

Competitive compensation

Paid time off

Job summary

EY is seeking an experienced agent AI Software Architect to design and implement memory architectures and data fabrics for complex enterprise AI. The role covers RAG, semantic chunking, multi-agent systems, and scalable inference, with hands-on coding and mentorship across the Knowledge/Data team.

The ideal candidate will have 5+ years in software engineering and AI, advanced degrees in EE/CS/Mathematics, and experience with AI frontier models and AI-native tools.

Qualifications

• Advanced degree in EE, CS or Math required.
• 5+ years in software engineering and AI.
• Experience with AI frontier models and memory/context architectures.
• Familiar with AI native development tools and CI/CD pipelines.

Responsibilities

• Design memory architectures for multi-agent systems to be replicated across AI-native platforms.
• Design memory/context systems including RAG and semantic chunking.
• Implement and benchmark architectures against AI and human evals.
• Create replicable integration frameworks for memory architectures across systems.
• Drive design requirements and implement via AI-native processes.
• Research emerging memory architectures and frontier model proposals.
• Collaborate with AI, Security, Data and Infrastructure teams for practical outcomes.
• Support business development for emerging technology as needed.
• Present at academic conferences and assist IP filings.
• Hands-on coding and mentoring Knowledge/Data Team members.

Skills

Memory architectures

Multi-agent systems

RAG & semantic search

AI tools

Python

Go/Rust/Java

CI/CD

NVIDIA NVAIE/Azure AI stacks

Education

Advanced degree in Electrical Engineering

Advanced degree in Computer Science

Advanced degree in Mathematics

Tools

NVIDIA NVAIE

Azure AI

Job description

EY is seeking an experienced agent AI Software Architect to design and implement memory architectures and data fabrics for complex enterprise AI. The role covers RAG, semantic chunking, multi-agent systems, and scalable inference, with hands-on coding and mentorship across the Knowledge/Data team.

The ideal candidate will have 5+ years in software engineering and AI, advanced degrees in EE/CS/Mathematics, and experience with AI frontier models and AI-native tools.