19 Nov
|
Straive
|
Chennai
Position: Senior Security Specialist
Experience: 5-8 years in Application Security, Offensive Security, or Penetration Testing
Location: India (Noida, Chennai, Hyderabad, And Bengaluru)
About the Role
Straive is looking for an experienced, hands-on Senior Security Specialist to support its Generative AI security and evaluation services.
The role involves conducting adversarial security assessments of Large Language Models (LLMs), Retrieval-Augmented Generation (RAG) applications, AI-powered chatbots, and agentic AI systems.
The selected candidate will work closely with Straive's AI engineering and delivery teams, contributing specialized offensive-security expertise, conducting vulnerability assessments, and supporting the development of standardized red-teaming methodologies.
The position requires strong technical capabilities, an investigative mindset, and the ability to translate security findings into actionable recommendations for enterprise clients.
This is primarily a hands-on technical role involving security assessments, automation, vulnerability investigation, and collaboration with cross-functional teams.
Key Responsibilities
1. Security Testing and Evaluation
- Conduct hands-on adversarial testing of LLM applications, RAG pipelines, and AI agents.
- Identify and validate vulnerabilities involving prompt injection, jailbreaking, sensitive information disclosure, insecure tool usage, and unauthorized access.
- Evaluate application-level security risks involving APIs, authentication, authorization, and external integrations.
- Investigate complex attack scenarios, reproduce vulnerabilities, and document technical findings.
- Recommend remediation measures and perform validation testing.
2. Red-Teaming Tools and Automation
- Work with AI red-teaming frameworks such as Microsoft PyRIT, Promptfoo, NVIDIA garak, and Giskard.
- Develop and customize Python-based scripts for adversarial testing and security automation.
- Combine automated vulnerability scanning with manual security investigations.
- Contribute to reusable test cases, attack scenarios, evaluation datasets,
and reporting templates.
- Support improvements in testing processes, automation, and assessment coverage.
3. Technical Collaboration
- Collaborate with AI engineers, evaluation specialists, and delivery teams to understand application architectures and potential security risks.
- Participate in technical discussions, security reviews, and vulnerability investigations.
- Provide technical guidance and share relevant expertise with colleagues during assessments.
- Review technical findings, where required, to ensure accuracy and reproducibility.
- Contribute to consistent testing practices and assessment quality.
- Support proof-of-concept demonstrations and technical evaluations when required.
- Execute security assessments within agreed testing boundaries.
- Prepare technical reports covering identified vulnerabilities, supporting evidence, severity, business impact, and remediation recommendations.
Required Technical Skills
Application and Offensive Security
- Solid hands-on experience in web application and API penetration testing.
- Understanding of authentication, authorization, access controls, injection vulnerabilities, and data security.
- Experience identifying, reproducing, and documenting security vulnerabilities.
- Familiarity with established security testing methodologies and tools.
Generative AI Security
- Working knowledge of Generative AI applications, including LLMs, RAG architectures, AI agents, and their associated security risks.
- Understanding of prompt injection, jailbreak techniques, sensitive data leakage, and insecure tool interactions.
- Familiarity with OWASP LLM Top 10, OWASP Agentic AI Top 10, and MITRE ATLAS is desirable.
Programming and Automation
- Proficiency in Python programming and scripting.
- Experience working with REST APIs, HTTP protocols, and security automation.
- Ability to develop or customize security testing scripts.
- Exposure to PyRIT, Promptfoo, garak, Giskard, or similar frameworks is desirable.
Preferred Certifications Hands-on Security Certifications
At least one of the following is strongly preferred:
- Offensive Security Certified Professional (OSCP / OSCP+)
- Offensive Security Web Expert (OSWE)
- Burp Suite Certified Practitioner (BSCP)
- GIAC Web Application Penetration Tester (GWAPT)
- Equivalent practical CREST certification
Equivalent demonstrated offensive-security experience may substitute for formal certifications.
Experience and Qualifications
Required
- 58 years of relevant experience in application security, offensive security, penetration testing, or related cybersecurity disciplines.
- Working knowledge of Generative AI applications, including LLMs, RAG architectures, AI agents, and associated security risks.
- Demonstrated ability to independently identify, reproduce, and explain application security vulnerabilities.
- Experience in security assessments, vulnerability analysis, and technical reporting.
- Proficiency in Python scripting and security testing automation.
- Strong analytical, problem-solving, communication, and documentation skills.
- Ability to collaborate effectively with cross-functional engineering and delivery teams.
Desirable
- Hands-on experience in security testing or vulnerability assessments of GenAI/LLM applications. Prior commercial AI red-teaming experience is an advantage but not mandatory.
- Experience using AI red-teaming frameworks such as PyRIT, Promptfoo, garak, or Giskard.
- Knowledge of adversarial testing techniques for RAG systems and AI agents.
- Experience developing reusable security testing scripts, methodologies, or automation workflows.
- Experience contributing to technical reviews and knowledge-sharing activities.
📌 Senior Security Specialist (Chennai)
🏢 Straive
📍 Chennai