Careers

Member of Technical Staff

About Incalmo

Incalmo is a team of researchers that have published at top academic conferences across security, ML, and systems (e.g., IEEE S&P, ICLR, NSDI, etc.). Multiple of our research projects were done in collaboration with frontier labs to further push our understanding of AI agent cyber capabilities.

What we do

Incalmo uses self-play and reinforcement learning to create extremely high-quality cyber environments to train models to be better at cybersecurity. We both partner with other security frontier labs and use these environments internally to post-train cyber capable models.

What you will do

You will work in an extremely fast-paced (and fun!) environment doing research on the frontier of AI cyber capabilities. This involves building systems that generate cyber data at scale, doing open-ended capability research, and post-training cyber-capable models.

We are looking for ambitious, high-agency, and mission-driven security researchers. Ideally, you have a background in: academic research in security, systems, or AI; a track record of doing cyber evaluations, and deep domain expertise in an area of cyber (e.g., malware, systems, etc.).

Get in touch

Email us at careers@incalmo.ai and send us something cool you have built related to systems, security, or AI.