LLM Security Tester

Job Description: LLM Security Tester

Job Title: LLM Security Tester

Experience: 1–5 Years

Location: Hyderabad / As per business requirement

Employment Type: Full-Time

Role Overview

We are looking for an LLM Security Tester responsible for designing, developing, and executing security testing strategies for Large Language Model (LLM) applications, Retrieval-Augmented Generation (RAG) systems, and AI agent-based solutions. The ideal candidate will identify vulnerabilities, perform security assessments, and improve the safety and reliability of AI applications.

The candidate will collaborate with AI/ML engineers, security teams, data scientists, and engineering stakeholders to evaluate AI risks and deliver secure, scalable, and trustworthy AI solutions.

Key Responsibilities

• Perform security testing for LLM applications, RAG systems, and AI agent workflows.
• Identify and analyze vulnerabilities including prompt injection, jailbreak attacks, data leakage, and unauthorized information exposure.
• Conduct AI red teaming activities to evaluate model behavior, security risks, and potential attack scenarios.
• Perform tool-abuse testing for AI agents, APIs, plugins, and external integrations.
• Develop security test cases and frameworks for evaluating LLM application vulnerabilities.
• Assess risks related to prompt manipulation, unsafe outputs, hallucinations, and model misuse.
• Analyze AI application architecture and identify potential security gaps.
• Document security findings, risk assessments, and recommended mitigation strategies.
• Collaborate with engineering teams to implement security improvements and best practices.
• Support the development of secure AI deployment processes and governance standards.

Required Skills & Qualifications

• 1–5 years of overall experience in AI security, cybersecurity, machine learning, application security, or related fields.
• Minimum 1–2 years of hands-on experience in LLM security testing or closely related technologies.
• Strong understanding of:
• Large Language Models (LLMs)
• Generative AI applications
• Retrieval-Augmented Generation (RAG)
• AI Agent architectures
• LLM vulnerabilities and attack techniques
• Hands-on experience with:
• Prompt injection testing
• Data leakage testing
• AI red teaming
• Tool abuse testing
• Security vulnerability assessment
• Security reporting
• Strong programming skills in Python.
• Experience testing AI applications and identifying security risks.
• Ability to analyze AI workflows and identify potential attack vectors.
• Strong problem-solving and analytical skills.

Good to Have Skills

• Experience with LLM security frameworks and testing methodologies.
• Knowledge of OWASP Top 10 for LLM Applications.
• Experience with AI safety and responsible AI practices.
• Familiarity with:
• LangChain
• LangGraph
• OpenAI APIs
• Azure OpenAI
• Hugging Face Transformers
• Vector databases
• Understanding of secure AI development lifecycle and MLOps practices.
• Experience with penetration testing or vulnerability assessment tools.
• Research experience in AI security, LLM vulnerabilities, or adversarial testing.

Candidate Profile Details Required

Please share the below details along with your updated resume:

Total Experience:

Relevant Experience:

Current Company:

Current CTC:

Expected CTC:

Notice Period:

Current Location:

Reason for Change:

Availability for Interview:

Updated Resume:

Interested candidates can share their updated profile at:

[Confidential Information]