Agentic AI Software Research Intern

Intel Corporation • Santa Clara, CA

23h • Hybrid

About The Position

We are looking for a Summer Research + Engineering Intern to join our team and work on agentic AI software solutions - systems where LLMs autonomously plan, reason, use tools, and act across complex, multi-step tasks. This is a hybrid role that blends research exploration with hands-on engineering: interns will prototype novel agent architectures, run experiments to evaluate agent capabilities, and ship working software that contributes directly to the team's goals. Interns will be paired with a senior mentor and work alongside ML engineers and research scientists. This is a rare opportunity to contribute to frontier AI engineering at the undergraduate level, in an environment that values curiosity, ownership, and the ability to learn fast. Strong candidates from prior cohorts at leading AI labs and research institutions have gone on to full-time offers or graduate school placements in AI. Responsibilities: Day-to-day work will span both research and implementation, and may include: Designing and prototyping AI agent architectures - building agents capable of multi-step planning, tool use, memory retrieval, and environment interaction Implementing multi-agent systems - orchestrating multiple specialized agents to collaborate on complex, long-horizon tasks using open-source agentic frameworks Integrating agents with external tools and APIs - connecting LLM-based agents to backend services, databases, code execution sandboxes, and web APIs Building and running evaluations - designing rigorous benchmarks and evaluation harnesses to measure agent reliability, reasoning quality, and task success rate Conducting literature reviews and experiments - surveying state-of-the-art agentic AI research, implementing baselines, and running ablations to identify what works Optimizing agent behavior - identifying failure modes such as context-window degradation, high latency, and weak spatial reasoning, and iterating on prompting strategies, memory systems, and tool-use logic Documenting architecture decisions - producing clear technical write-ups, diagrams, and code documentation so work is reproducible and shareable Presenting findings to the team - communicating research results and engineering decisions in weekly syncs and a final intern project presentation

Requirements

• Currently enrolled in a Bachelor's degree program in Computer Science, Computer Engineering, Mathematics, Statistics, or a related technical field
• Intellectual curiosity: Genuinely excited about agentic AI, autonomous systems, and the research questions that make them hard.
• Builder mentality: Wants to ship working prototypes quickly, learn from failures, and iterate fast.
• Requirements listed would be obtained through a combination of industry relevant job experience, internship experiences and or schoolwork/classes/research.

Nice To Haves

• Python proficiency: Strong, practical Python coding skills - comfortable writing clean, testable, modular code.
• Software engineering fundamentals: Comfort with Git/version control, debugging, API integration, and basic data structures and algorithms.
• Machine learning foundations: Coursework or practical experience in machine learning, deep learning, or NLP - understanding of how neural networks learn, what training and inference mean, and basic model evaluation.
• Familiarity with LLMs: Experience working with LLMs and understanding of prompt engineering, context windows, and model capabilities
• Curiosity and learning agility: Ability to pick up new frameworks and concepts quickly, debug when things break, and make progress on loosely defined problems.
• Communication skills: Ability to explain technical work clearly in writing and verbally, to both technical and non-technical audiences.

Responsibilities

• Designing and prototyping AI agent architectures - building agents capable of multi-step planning, tool use, memory retrieval, and environment interaction
• Implementing multi-agent systems - orchestrating multiple specialized agents to collaborate on complex, long-horizon tasks using open-source agentic frameworks
• Integrating agents with external tools and APIs - connecting LLM-based agents to backend services, databases, code execution sandboxes, and web APIs
• Building and running evaluations - designing rigorous benchmarks and evaluation harnesses to measure agent reliability, reasoning quality, and task success rate
• Conducting literature reviews and experiments - surveying state-of-the-art agentic AI research, implementing baselines, and running ablations to identify what works
• Optimizing agent behavior - identifying failure modes such as context-window degradation, high latency, and weak spatial reasoning, and iterating on prompting strategies, memory systems, and tool-use logic
• Documenting architecture decisions - producing clear technical write-ups, diagrams, and code documentation so work is reproducible and shareable
• Presenting findings to the team - communicating research results and engineering decisions in weekly syncs and a final intern project presentation

Benefits

• We offer a total compensation package that ranks among the best in the industry. It consists of competitive pay, stock bonuses, and benefit programs which include health, retirement, and vacation.
• Find out more about the benefits of working at Intel.

What This Job Offers

• Career Level: Intern
• Number of Employees: 5,001-10,000 employees