Description

Job Details:

Job Description:
Intel is transforming to meet the demands of a rapidly changing world. We design and deliver industry-leading technology that powers data centers, enables AI, and drives the future of computing. Join a team building the software and platforms developers use to deliver reliable AI performance at scale. In this internship, you will help design and run benchmarks for agentic AI systems - LLM-based agents that plan, reason, use tools, and execute multi-step workflows - with a focus on understanding and optimizing end-to-end performance on Intel platforms. You will build on this work: profiling real agentic workloads, decomposing latency across inference and task execution, and identifying where Intel hardware and software can make a measurable difference in the end-to-end efficiency of the system. You will then extend these benchmark span to cover more agentic case including multimodality and swarm of agent systems. This role has a strong research component: you'll reproduce and extend published benchmarks, run structured experiments on Intel platforms, and synthesize findings into clear recommendations, demos, and documentation that can influence our engineering and enablement priorities. You will be collaborating with the teams developing these optimizations. Responsibilities:
• Profile and benchmark agentic AI workflows end-to-end, decomposing latency between LLM inference and CPU-bound task execution (compilation, scripting, data processing, sandbox orchestration)
• Reproduce and extend published agentic benchmarking suites (e.g., Raj et al.'s multi-workload profiling, AMA-Bench memory evaluation) on Intel Xeon platforms
• Design experiments to measure agentic-specific performance dimensions: sandbox spin-up/teardown, multi-model co-location, memory-intensive agent workloads, and orchestration overhead
• Evaluate agent behavior, performance, and failure modes across multi-step tasks
• Explore how Intel platform features (AMX, large DRAM capacity, virtualization, TDX) impact agentic workload performance and security
• Document experiments, results, and technical learnings through reports, demos, or upstream contributions

Qualifications:

Minimum qualifications:

• Currently pursuing a Master's or PhD in Computer Science, AI, Systems, or a related field and 3+ months of academic or work experience in/with:

• Programming skills in Python; experience with systems profiling or performance analysis is a plus

• Core AI/ML concepts (NLP, reasoning, reinforcement learning, or decision-making systems)

• Experimenting with LLMs, APIs, or AI tooling

• Exposure to agent-based AI frameworks, orchestration tools, or multi-agent systems

• Ability to quickly prototype, run experiments, analyze results, and iterate

Preferred

• Experience with performance benchmarking, workload characterization, or latency profiling

• Familiarity with Linux systems, containers/VMs, or cloud development environments

• Understanding of CPU architecture concepts (caches, NUMA, vectorization) is a bonus

• Strong communication skills and ability to clearly present experimental findings

Job Type:
Student / Intern

Shift:
Shift 1 (United States of America)

Primary Location:
US, Oregon, Hillsboro

Additional Locations:

Business group:
The Software Team drives customer value by enabling differentiated experiences through leadership AI technologies and foundational software stacks, products, and services. The group is responsible for developing the holistic strategy for client and data center software in collaboration with OSVs, ISVs, developers, partners and OEMs. The group delivers specialized NPU IP to enable the AI PC and GPU IP to support all of Intel's market segments. The group also has HW and SW engineering experts responsible for delivering IP, SOCs, runtimes, and platforms to support the CPU and GPU/accelerator roadmap, inclusive of integrated and discrete graphics.

Posting Statement:
All qualified applicants will receive consideration for employment without regard to race, color, religion, religious creed, sex, national origin, ancestry, age, physical or mental disability, medical condition, genetic information, military and veteran status, marital status, pregnancy, gender, gender expression, gender identity, sexual orientation, or any other characteristic protected by local law, regulation, or ordinance.

Position of Trust
N/A

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 .

Annual Salary Range for jobs which could be performed in the US: $142,900.00-193,400.00 USD

The range displayed on this job posting reflects the minimum and maximum target compensation for the position across all US locations. Our standard internship rates are based on your degree, location, and the job role. Your recruiter can share more about the specific compensation range for your preferred location and job role during the hiring process.

Work Model for this Role
This role will be eligible for our hybrid work model which allows employees to split their time between working on-site at their assigned Intel site and off-site. * Job posting details (such as work model, location or time type) are subject to change.

*

ADDITIONAL INFORMATION: Intel is committed to Responsible Business Alliance (RBA) compliance and ethical hiring practices. We do not charge any fees during our hiring process. Candidates should never be required to pay recruitment fees, medical examination fees, or any other charges as a condition of employment. If you are asked to pay any fees during our hiring process, please report this immediately to your recruiter.
Requisition #: JR0282612

pca3lyuhf