AI Security Engineer / Researcher (IR-558)
Intellectsoft (company site, opens in a new tab)3+ yrsBengaluruHybridDirect career pageEst. 14–28 LPA
Posted 18h ago
Reach people at Intellectsoft
People at this company you can reach
Log in to see who works here
Create a free account or log in to see the people at Intellectsoft you could write to:
- Recruiters & HR
- People in this function
- Work addresses
Your match
Against your primary resume
Log in to see your match score
Create a free account or log in to unlock your CV match score across:
- Role fit
- Experience
- Industry relevance
Protocol Intelligence
How competitive this role is
Competition
Background fit
Strictness
Log in to see why each signal reads the way it does.
Job description
Structured overview of role & requirements
About This Role
- Own end-to-end AI security research across modern AI stack including generative systems, LLM copilots, training/data pipelines, and AI governance.
- Design, build, and maintain agentic systems from prototype to scalable production with operational responsibility for deployment, monitoring, and cost management.
- Develop rigorous evaluation infrastructure, integrate enterprise systems as agent tools, and translate client requirements into secure AI solutions with clear stakeholder communication.
Minimum Requirements
- 3+ years in security research, offensive security, ML/AI security, detection engineering, or related disciplines.
- Strong Python programming skills for building research tooling, async services, CLIs, and automated pipelines.
- Hands-on expertise in at least one AI attack surface: LLM apps, agentic workflows, or ML training/inference pipelines.
- Solid understanding of application security fundamentals, threat modeling for autonomous and transformer-based systems.
Ideal Candidate Profile
- Experienced in vulnerability analysis, adversarial ML, detection engineering, and secure SDLC practices with both offensive and defensive security knowledge.
- Familiarity with LLM architectures, retrieval-augmented generation, prompt injection, tool calling, and relevant ML and AppSec tooling.
- Capable of translating security research and CVEs into operational exploits and defensive controls, with experience designing statistically rigorous experiments and validating security controls in real environments.