Job Title : Red Teaming Location State : Karnataka/ Tamil Nadu/ Maharashtra Location City : Bangalore/ Chennai/ Mumbai/ Pune Experience Required : 3 to 4 Year(s) Shift: Flexible for Shifts Work Mode: Work from Home Position Type: Contract Openings: 5 Company Name: VARITE INDIA PRIVATE LIMITED Interested candidate share there updated resume sangeeta.t@varite.com For more information contact sangeeta @ 8929376486 About The Job: Essential Job Functions: Expertise in Prompt Engineering: Develop and craft diverse and complex prompts aimed at testing various aspects of LLM behaviour, including but not limited to bias, accuracy, coherence, and ethical considerations. Refine and iterate using advanced prompts based on models initial responses to identify how slight changes affect the output, with the goal of bypassing the model's filters. Vulnerability Assessment: Identify and analyse potential vulnerabilities and flaws in LLM responses by executing a variety of prompt scenarios. Document findings and provide detailed reports on discovered issues. Adversarial Prompting Techniques: Manipulating language, phrasing, and context to bypass built-in protections. This could include rephrasing sensitive requests in ways that avoid triggering content filters (e.g., asking for sensitive information in a polite or indirect manner) and prompt injection attacks, where a carefully crafted prompt is designed to override the models instructions or system prompts (e.g., attempting to break internal instructions set by developers). Design multi-turn interactions where previous responses are used to gradually lead the model to unsafe outputs. This involves testing for context-aware vulnerabilities and confusing the model. Probing Guardrails and Protection Layers: crafting prompts that probe the effectiveness of safety mechanisms like content moderation, censorship, or response limitations. Candidates need to have skill in crafting prompts in multiple languages to test whether guardrails are equally effective across different linguistic contexts. The successful candidate also needs to design prompts that test the LLMs compliance with ethical and legal standards (e.g., testing for responses related to illegal activities, child protection, or privacy breaches). Probing Guardrails and Protection Layers and Multi-Stage prompting: Crafting prompts and creating testing templates that probe the effectiveness of safety mechanisms like content moderation, censorship, or response limitations. Nice to have would be skills in multi-lingual testing of guardrails. Policy Non-Compliance checks: Checking the model responses against a corporate policy for compliance and probing for ways the model can be made to evade the guardrails. Reporting and collaboration: Evaluate the model and report vulnerabilities, test outcomes using standardised benchmarks like responsible AI, and collaborate with the protection/guardrails/Client team. Qualifications: Bachelors degree in computer science, Artificial Intelligence, Machine Learning, or a related field with more than 3 years of experience. Advanced degrees are a plus. Proven experience in AI/Client, with a focus on prompt engineering, model evaluation, or red teaming. Familiarity with LLMs and their potential vulnerabilities is highly desirable. Strong understanding of natural language processing (NLP) and LLMs. Expertise in prompt crafting and the ability to generate diverse and effective test cases. Proficiency in programming languages such as Python or R, with experience in AI/Client frameworks and tools. Ability to use scripting for automation. Excellent problem-solving skills and a creative approach to challenge AI systems. Strong analytical and communication skills, with the ability to present complex findings clearly. Understanding the MITRE Telecommunication&CK framework is nice to have but not required. Prior experience with validating and probing models for policy compliance, including adversarial assessment, is nice to have but not required. Experience exploiting vulnerabilities in at least two of the following areas: web applications and cloud environments. Essential Job Functions: Red Teaming Experience: Automated scripting attacks (not manual). Experience with LLMs: Integration into automated workflows. LLM Vulnerability Analysis: Adversarial attacks and model evasion techniques. Prompt Engineering: Crafting and optimizing prompts for LLMs. Programming/Scripting Skills: Intermediate/advanced Python scripting for automation and manual attack workflows. Operating Systems:. Networking Penetration Testing: Strong expertise required. MySQL: Securing databases and identifying vulnerabilities Well aware of attacks like Hallucination, Manipulation is required How to Apply: Interested candidates are invited to submit their resume using the apply online button on this job post. Equal Opportunity Employer: VARITE is an equal opportunity employer. We celebrate diversity and are committed to creating an inclusive environment for all employees. We do not discriminate on the basis of race, color, religion, sex, sexual orientation, gender identity or expression, national origin, age, marital status, veteran status, or disability status. Unlock Rewards: Refer Candidates and Earn. If you're not available or interested in this opportunity, please pass this along to anyone in your network who might be a good fit and interested in our open positions. VARITE offers a Candidate Referral program, where you'll receive a one-time referral bonus based on the following scale if the referred candidate completes a three-month assignment with VARITE. Exp Req - Referral Bonus 0 - 2 Yrs. - INR 5,000 2 - 6 Yrs. - INR 7,500 6 + Yrs. - INR 10,000 About VARITE: VARITE is a global staffing and IT consulting company providing technical consulting and team augmentation services to Fortune 500 Companies in USA, UK, CANADA and INDIA. VARITE is currently a primary and direct vendor to the leading corporations in the verticals of Networking, Cloud Infrastructure, Hardware and Software, Digital Marketing and Media Solutions, Clinical Diagnostics, Utilities, Gaming and Entertainment, and Financial Services.
