DeepRec.ai is supporting a high-growth cybersecurity startup building security solutions for the AI era, focused on protecting AI applications, agents, identity infrastructure, and sensitive enterprise data.
(Fully remote position)
We're looking for a Threat Researcher with a strong offensive security background to research emerging attack techniques across AI and enterprise environments.
What You'll Do
Research attacks against LLMs, AI agents, APIs, identity systems, and data flows
Investigate prompt injection, agent manipulation, token abuse, privilege escalation, and data exfiltration
Develop threat models, attack simulations, and working PoCs
Build research tooling and test environments using Python, Docker, and cloud platforms
Collaborate with engineering and product teams to turn research into defensive capabilities
Publish original research through blogs, talks, advisories, or open-source tooling
Apply frameworks such as MITRE ATT&CK to emerging AI attack techniques
What We're Looking For
6–10 years in threat research, red teaming, offensive security, or security engineering
Strong hands-on offensive security and vulnerability research experience
Deep understanding of AI/LLM and agentic architectures
Strong knowledge of IAM, OAuth/OIDC, tokens, privileges, and DLP
Strong Python and cloud/container experience
Track record of publicly shared security research, tooling, or technical writing
Ability to communicate complex security research clearly to technical and non-technical audiences
This is a highly hands-on research role with significant ownership over the research agenda and the opportunity to work on new attack surfaces emerging from increasingly autonomous AI systems.