PhD Research Intern: Agentic AI for Enterprise Systems

IBM; Town of Yorktown (NY); On-site; USD 89,000 - 164,000; Full time

Job summary

IBM Research invites a PhD student to join the AI Native Systems team for a 2027 summer internship focused on advancing agentic AI systems for IBM Z. You will explore large language models, AI agents, and memory management, developing adaptive mechanisms within the Finn/Paver framework and evaluating them on on-platform z/OS tasks.

You will collaborate with IBM researchers and academics to translate research into practical architectures, potentially yielding publications and IP disclosures while

Qualifications

• Pursuing a PhD in a related field (CS/CE/AI).
• Experience in ML/DL, LLMs, AI agents, NLP or related AI research areas.
• Strong Python programming skills and ML framework experience.

Responsibilities

• Research adaptive information-control mechanisms for agentic AI systems in IBM Z environments.
• Define and model minimal sufficient agent state including observations, evidence, memory, history, tools and progress.
• Develop and evaluate information acquisition, retrieval, summarization, memory management, and context compression techniques.

Skills

ML

DL

LLMs

AI agents

NLP

Python

Education

Master's Degree

Doctorate Degree

Tools

Python

PyTorch

TensorFlow

Job description

IBM Research invites a PhD student to join the AI Native Systems team for a 2027 summer internship focused on advancing agentic AI systems for IBM Z. You will explore large language models, AI agents, and memory management, developing adaptive mechanisms within the Finn/Paver framework and evaluating them on on-platform z/OS tasks.

You will collaborate with IBM researchers and academics to translate research into practical architectures, potentially yielding publications and IP disclosures while