Lead AI Memory Architect for Multi-Agent Systems

EY; Richmond (VA); Hybrid; USD 126,000 - 230,000; Full time

Benefits offered by this job

Hybrid work model

Comprehensive compensation & benefits

Medical & dental coverage

Pension and 401(k)

Paid time off

Job summary

EY is actively seeking an experienced agent AI Software Architect to design memory architectures and context systems for multi-agent enterprises. You will develop reproducible frameworks, drive design requirements, and benchmark with rigorous evals while mentoring the Knowledge/Data team.

The role emphasizes AI frontier models, distributed inference, and collaboration across AI, Security, Data and Infra teams in a fast-paced environment.

Qualifications

• Advanced degree required in technical field.
• 5+ years of software engineering and AI experience.
• Experience with AI frontier models and memory/context architectures.
• Familiar with AI native development tools and code assistance.
• Proficiency in scripting and software languages (Python, Bash, Go, Rust, Java).
• Understanding of model fine tuning and context management (RAG, SFT, LoRA/PEFT).
• Experience with CI/CD and modern development tools.
• Experience with Nvidia NVAIE and Azure AI stacks.

Responsibilities

• Design memory architectures for multi-agent systems to be replicated across AI native designed systems.
• Design of context systems including RAG and Skills with semantic chunking and search.
• Implement and test these architectures benchmarking performance against agent and human designed evals.
• Design replicable integration frameworks for use of memory architecture across multiple systems.
• Drive agent design requirements and implement through AI Native design process.
• Assess through primary and secondary research emerging memory architectures and frontier model proposals.
• Collaborate with other architectural experts in AI, Security, Data and Infrastructure to insure balanced and practical outcomes.
• Support strategic business development activities for emerging technology as required.
• Present at academic conferences and support development of IP filings
• Hands on coding and mentoring other members of the Knowledge / Data team

Skills

AI memory architectures

Multi-agent design patterns

RAG & semantic chunking

Distributed inference optimization

Mentorship & leadership

Python scripting

Education

Advanced degree in Electrical Engineering, Computer Science or Mathematics

Tools

Cursor

Claude Code

Qodo/Codium

Gemini

AWS Q

GitHub

NVIDIA NVAIE

Azure AI stacks

Job description

EY is actively seeking an experienced agent AI Software Architect to design memory architectures and context systems for multi-agent enterprises. You will develop reproducible frameworks, drive design requirements, and benchmark with rigorous evals while mentoring the Knowledge/Data team.

The role emphasizes AI frontier models, distributed inference, and collaboration across AI, Security, Data and Infra teams in a fast-paced environment.