Keysight is at the forefront of technology innovation, delivering breakthroughs and trusted insights in electronic design, simulation, prototyping, test, manufacturing, and optimization. Our ~15,000 employees create world-class solutions in communications, 5G, automotive, energy, quantum, aerospace, defense, and semiconductor markets for customers in over 100 countries. Learn more about what we do.
Our award-winning culture embraces a bold vision of where technology can take us and a passion for tackling challenging problems with industry-first solutions. We believe that when people feel a sense of belonging, they can be more creative, innovative, and thrive at all points in their careers.
We are offering a research-driven security internship for students who enjoy solving complex technical problems and want to gain hands-on experience in cryptography, high-performance computing, and hardware security.
During this internship, you will work closely with experienced researchers and engineers on real security research topics, combining theoretical foundations with practical experimentation and development. The focus is on understanding how cryptographic implementations behave under stress — and how they can be improved.
On a day-to-day basis, you will write code, run experiments, discuss ideas with your mentor, and turn technical findings into clear results. You don’t need to be an expert in everything on day one — strong fundamentals, curiosity, and motivation to learn matter most.
The internship can be completed as a minimum 3-month placement or extended into a 6-month thesis project, depending on academic requirements.
What we offer:
Paid internship, with travel allowance
Work laptop (for interns based in the Netherlands)
Access to Keysight equipment, depending on the topic
Lunch at work
You might enjoy this internship if you like figuring out how systems work under the hood, enjoy experimenting with code and learning by doing, and prefer open-ended technical challenges over predefined instructions.
Responsibilities
"Can small functionality-preserving modifications to code, such as misleading identifiers or structural cues and lightweight code transformations lead LLMs to confidently misinterpret program behavior?"
The thesis looks at how well LLMs actually hold up when analyzing code, specifically by testing whether small but carefully crafted changes to code can trick them into drawing the wrong conclusions. The main idea is to use misleading semantic cues, like deceptive variable names and familiar-looking but misrepresentative patterns, to misdirect the model's reasoning. On top of that, some lightweight structural transformations will be used to reinforce the misdirection. The goal is to better understand where and how LLMs fail in code analysis scenarios, and what that means for the broader use of AI in reverse engineering.
Qualifications
General Requirements
Currently enrolled as a Bachelor, Master, or PhD student
Ability to work independently while collaborating effectively within a team
Good command of English, written and spoken
Availability for at least 3 months, minimum 4 days per week
Eligibility to work in the Netherlands / EU for the duration of the internship
Specific Requirements
Experience with LLM prompting and evaluation techniques
- Binary analysis and reverse engineering skills
- Exposure with Code transformation and obfuscation methods
- Data collection and experimental analysis
- Scripting and automation experience
Careers Privacy Statement***Keysight is an Equal Opportunity Employer.***
