We are seeking a Senior AI Security Researcher. In this role, you will be responsible for building world-class solutions that detect and prevent attacks against AI applications, LLMs, and autonomous agents, including prompt injections, jailbreaks, data leakage, and other emerging AI-native threats.
What is the job:
This is a senior hands-on role for someone who combines deep AI expertise with a strong research mindset and the ability to build production-grade systems. We are looking for an independent, highly capable person who can take an idea from research, through model development and evaluation, all the way to scalable production deployment. We are looking for someone who can invent, validate, build, and ship.
What will you do?
Lead hands-on AI research and development for our next-generation cybersecurity capabilities.
Lead the development of advanced AI-driven protections for emerging threats against AI agents
Fine-tune, adapt, evaluate, and optimize AI models, including open-source LLMs, embedding models, and classifiers.
Turn research ideas into reliable production capabilities with strong accuracy, low latency, and long-term robustness
Collaborate with research, engineering, product, and field teams to integrate new capabilities into our products.
Requirements: 3+ years of hands-on experience in AI, machine learning, NLP, deep learning, or production ML systems.
Strong experience with LLMs, transformer-based models, embedding models and text classification.
Proven ability to fine-tune, evaluate, optimize, and deploy AI models in production.
Hands-on experience with AI frameworks such as PyTorch, Hugging Face, Sentence Transformers, vLLM, or similar tools.
Research mindset with strong execution skills, independence, ownership, and ability to lead complex initiatives end-to-end.
M.Sc. or Ph.D. in Computer Science, Machine Learning, Data Science, Cybersecurity, or a related field.
This position is open to all candidates.