The posting
At IBM Research, we are the innovation engine of IBM. Exploring what’s next in computing and shaping the technologies the world will rely on tomorrow. From advancing AI and hybrid cloud to pioneering practical quantum computing, we anticipate challenges and unlock new opportunities for clients, partners, and society. Working in Research means joining a team that accelerates discovery at the intersection of high-performance computing, AI, quantum, and cloud. You’ll collaborate with leading scientists, engineers, and visionaries to push boundaries and turn ideas into reality. With a culture built on curiosity, creativity, and collaboration, IBM Research offers the opportunity to grow your career while contributing to breakthroughs that transform industries and change the world.
At the Dublin Research Lab, in the Security team we focus primarily on the Security and Privacy of GenAI. From research to product, we are interested in scientific contributions to the field, as well as real world innovative solutions. Currently we have varied internship opportunities across the area.
We would like to talk to people with a general interest in the security of generative AI. This includes
* model hardening approaches through curated data sets and advanced fine-tuning approaches, via e.g. differential privacy
* prompt inspection for security threats.
* model output analysis to ascertain levels of sensitive information leakage etc.
The internship will aim for publications in top-tier conferences, NeurIPS, AAAI, ICML,
* Working knowledge in deep learning and familiarity with NLP
* Strong Python programming skills
* Experience of working with deep learning libraries, e.g. TensorFlow, Pytorch, Keras and NLP tools, e.g. NLTK, Transformers, spaCy
* Solid understanding of mathematical concepts such as probabilities, statistics and linear algebra
.



