AI Security Research Engineer Intern
OneSpotAI
Bengaluru, Karnataka, IndiaFresher2h agovia LinkedIn
This job at a glance
- Who can apply
- Freshers and up to 1 year
- Must know
- PythonLLMsVulnerability managementGitContent writing
- Work
- On-site in Bengaluru · internship
- Pay
- Not stated by the employer.
- Skill demand
- LLMs65%Python52%Vulnerability management19%Git14%of 99 similar fresher jobs posted in India this week
- Listed
- 29 Oct 2026 · still open
Sign in free to see which of these skills your resume already shows.
About the Role
You will test AI agents for weaknesses, work out why they fail, and build the defenses that fix them. Your research goes directly into our product.
Key Responsibilities
- Probe AI agents for weaknesses such as tool misuse, privilege escalation, and data leakage
- Trace each issue to its root cause
- Build fixes including guardrails, access controls, and detection logic
- Create automated tests that confirm each fix holds over time
- Document findings in a form engineers can act on right away
Requirements & Tech Stack
- Strong Python skills
- Hands-on experience with LLM applications, agents, RAG, or MCP
- Basic understanding of threat modeling, red teaming, or vulnerability research
Qualifications
- Public work to show: GitHub projects, CTF writeups, blog posts, or research notes