Job Description
Hello\nGreetings from ZettaMine Labs Pvt Ltd!!\n\nWe are looking for LLM Security Evaluation Expert for PAN India.\n\nJob Role : LLM Security Evaluation Expert\nLocation : PAN India\nNotice Period : NA( As it is for Gig Workers)\nExperience : 3 to 6 years\nRelevant Exp : Minimum of 3 Years Experience in below list Skills\n\n'13; LLM architecture & training process knowledge\n'13; OWASP LLM Top 10 & MITRE ATLAS\n'13; Adversarial prompt design & execution\n'13; Vulnerability assessment for AI/ML systems\n'13; Prompt injection & jailbreaking techniques\n'13; Offensive security tooling & methodology\n'13; Role-playing and bias exploitation attacks\n'13; Security reporting and findings documentation\n\nMandatory :\n\n3+ years of experience in offensive security, AI/ML security research, penetration testing of AI systems, or dedicated LLM red-teaming.\nDeep working knowledge of LLM architecture, training processes, and alignment techniques (RLHF, fine-tuning, instruction-following).\nProven hands-on expertise in adversarial prompt design, jailbreaking, prompt injection, and role-play attack methodologies.\nStrong grounding in cybersecurity principles applied to AI/ML systems; familiarity with OWASP LLM Top 10 and related frameworks.\nClear and precise written communication skills — ability to document technical findings thoroughly and present security risks to non-technical stakeholders.\nCommitment to responsible testing practices and understanding of the ethical implications of AI security research.\n\nJob Description:\nAs a LLM Security Evaluation Expert, you will be the adversarial mind that frontier AI systems need but rarely have. Your mandate is to rigorously probe large language models for security vulnerabilities — designing, executing, and documenting adversarial prompt campaigns that expose real failure modes before bad actors find them first. You will operate at the intersection of offensive security and AI research , crafting sophisticated attack vectors including prompt injection, jailbreaking, role-play manipulation, and bias exploitation, and translating findings into actionable security intelligence for AI development teams.\n\nThis is not a compliance checkbox role.
It requires genuine adversarial creativity, deep LLM knowledge, and the discipline to document what you find with rigour and ethical clarity.\n\nKey Responsibilities:\n\nAdversarial Prompt Engineering & Attack Design\nDevelop and execute a structured suite of adversarial prompts — from foundational to highly sophisticated — targeting known and emerging LLM vulnerability classes\nDesign attacks to bypass safety filters and content moderation policies; induce leakage of sensitive or confidential information; manipulate outputs toward harmful, biased, or unintended content\nEngineer prompt injection, jailbreaking, role-playing, and model bias exploitation scenarios; test against a spectrum of LLM architectures and deployment configurations\n\nSecurity Evaluation & Vulnerability Analysis\nSystematically execute adversarial test campaigns against target LLMs; analyse responses to identify successful exploits, failure patterns, and exploitable security weaknesses\nConduct vulnerability assessments against published frameworks including OWASP LLM Top 10, MITRE ATLAS, and NIST AI RMF; document findings with reproducible methodology\nAssess the resilience of safety mechanisms including RLHF alignment, Constitutional AI, and fine-tuning guardrails against adversarial pressure.\n\nReporting, Standards & Collaboration\nProduce clear, technically precise vulnerability reports including exploit documentation, impact assessment, and remediation recommendations\nCollaborate with AI development and red-team leads to translate findings into security requirements, test standards, and policy updates\nContribute to Platina’s growing adversarial evaluation library and internal red-teaming playbooks.\n\nPlease provide following detail along with your updated profile to\n\nPrimary Skill -\nTotal Experience -\nRelevant Experience :\nCurrent location\nHighest Qualificaiton:\nExpertise/Stream:\nDomain :\n\nI will be reaching out to you over a call or email as soon as possible.\n\nThanks & Regards,\nVyshnavi
