Intern: AI Red Teaming (Fall 2026)

Posted 25d ago

You will try to break the systems we build and the models we protect, and turn what you find into something the team can act on: a reproducible attack, an evaluation that catches it, and a written account of why it works.
Expect some mix of: eliciting unsafe behaviour from aligned LLMs and multi-modal models; prompt injection and tool-use abuse against agentic systems; automating attack generation and evaluation rather than hand-crafting one-off prompts; and measuring whether guardrails hold under pressure. Where RealmLabs' interpretability work gives you access to a model's internals, use it.
We aim for a paper or public technical report out of every internship, plus attacks that stay in our evaluation suite after you leave.

Adversarial ML and Red Teaming

MUST HAVE prior red-teaming or pen-testing experience like DefCon CTFs or bugbounties. General SWE experience is not suitable for this role.
MUST HAVE Familiarity with agentic systems and their attack surface — tool calls, retrieval, memory, multi-agent orchestration.
Hands-on experience attacking or stress-testing models, from any direction: jailbreaks, prompt injection, adversarial examples, data poisoning, model extraction, or evaluating safety and moderation systems.
Able to read a paper and implement its attack.

Machine learning tools: pytorch, huggingface, transformers, datasets.
Applied deep learning and LLM experience.
Training and evaluating deep models.
(nice to have) finetuning LLMs, multi-modal LLMs.
(nice to have) Familiarity with ML[NLP,LLM,Vision] interpretability methods, sparse autoencoders, linear probes — as a way of locating failure modes, not as an end in itself.

Must be authorized to work in the USA or must be able to obtain CPT (Curricular Practical Training) approval from host university.

Skills