AI Memory Architect for Multi-Agent Systems — Hybrid

EY; Miami (FL); Hybrid; USD 126,000 - 230,000; Full time

Benefits offered by this job

Hybrid work model

Total Rewards package

Paid time off

Job summary

EY is seeking an experienced agent AI Software Architect to design and implement memory architectures and data fabrics for enterprise use cases. You will work on multi-agent systems, RAG, semantic chunking, and distributed inference, while mentoring team members and shaping IP strategy.

You’ll collaborate across AI, Security, Data and Infrastructure to deliver scalable AI solutions in a fast-paced environment, with hybrid work opportunities and a comprehensive Total Rewards package.

Qualifications

• Advanced degree in Electrical Engineering, Computer Science or Mathematics.
• 5+ years of experience in software engineering and AI.
• Experience with AI frontier models and memory/context architectures.
• Proficiency with AI-native development tools / code assist (Cursor, Claude Code, Qodo/Codium, Gemini, AWS Q, GitHub).
• Familiarity with Python, Bash and Go, Rust, Java, etc.
• Understanding of AI native design process and core principles.
• Deep understanding of model tuning and customization (RAG, SFT, LoRA/PEFT).
• Experience with IDEs, CI/CD, code hosting (GitHub/GitLab/Azure DevOps).
• Experience with Nvidia NVAIE and Azure AI stacks.

Responsibilities

• Design memory architectures for multi-agent systems to be replicated across AI-native designs.
• Design context systems including RAG and Skills with semantic chunking and search.
• Implement and test architectures benchmarking against agent and human evals.
• Design replicable integration frameworks for memory architectures across systems.
• Drive agent design requirements through AI-native design processes.
• Assess emerging memory architectures and frontier model proposals.
• Collaborate with architecture teams in AI, Security, Data and Infrastructure.
• Support strategic business development activities for emerging tech.
• Present at academic conferences and support IP filings.
• Hands-on coding and mentoring Knowledge/Data team members.

Skills

AI memory architectures

Context design for AI

Multi-agent memory systems

RAG and semantic chunking

Fine-tuning / customization (LoRA/PEFT

NVIDIA NVAIE

Azure AI stacks

Python

Go / Rust / Java

CI/CD pipelines

Code assistants (Cursor, Claude Code,Q

Education

Advanced degree in Electrical Engineering, Computer Science or Mathematics

Tools

Cursor

Claude Code

Qodo/Codium

Gemini

AWS Q

GitHub

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 enterprise use cases. You will work on multi-agent systems, RAG, semantic chunking, and distributed inference, while mentoring team members and shaping IP strategy.

You’ll collaborate across AI, Security, Data and Infrastructure to deliver scalable AI solutions in a fast-paced environment, with hybrid work opportunities and a comprehensive Total Rewards package.