Memory AI Architect for Multi-Agent Systems

EY; City of Albany (NY); Hybrid; USD 151,000 - 262,000; Full time

Job summary

EY in the United States is hiring an experienced agent AI Software Architect to design and implement memory architectures and data fabrics for complex enterprise use cases. The role focuses on multi-agent systems, RAG, semantic chunking, and scalable inference, with a strong emphasis on practical, enterprise-ready solutions.

You will mentor the Knowledge/Data team, work with cross-functional groups, and contribute to IP filings and academic presentations.

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.
• Use of AI native development tools (Cursor, Claude Code, Qodo/Codium, Gemini, AWS Q, GitHub).
• Familiarity with Python, Bash and languages such as Go, Rust, Java.
• Understand AI native design process and principles.
• Deep understanding of model fine tuning via context management (RAG, SFT, LoRA/PEFT).
• Experience with IDEs, CI/CD pipelines, and collaboration tools (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 semantic chunking and search.
• Implement and test architectures, benchmarking against agent and human evals.
• Create replication-friendly integration frameworks for memory architectures.
• Drive agent design requirements through AI-native design processes.
• Research emerging memory architectures and frontier model proposals.
• Collaborate with AI, Security, Data and Infrastructure experts for balanced outcomes.
• Support strategic business development for emerging tech as needed.
• Present at academic conferences and assist IP filings.
• Hands-on coding and mentoring Knowledge/Data team members.

Skills

AI memory design

Multi-agent systems

Cross-functional leadership

Problem solving

Communication

Hybrid collaboration

Education

Advanced degree in Electrical Engineering, Computer Science or Mathematics

Tools

Cursor

Claude Code

Qodo/Codium

Gemini

GitHub

Job description

EY in the United States is hiring an experienced agent AI Software Architect to design and implement memory architectures and data fabrics for complex enterprise use cases. The role focuses on multi-agent systems, RAG, semantic chunking, and scalable inference, with a strong emphasis on practical, enterprise-ready solutions.

You will mentor the Knowledge/Data team, work with cross-functional groups, and contribute to IP filings and academic presentations.