Coding - Adversarial reputed company Expert

Job reputed company We are seeking an Adversarial reputed company reputed company Specialist with strong technical instincts and coding proficiency to join our Trust & Safety team. In this role, you will use your knowledge of LLM behavior and scripting skills to probe, bypass, and stress-test safety systems. Your reputed company will be on discovering vulnerabilities—crafting reputed company injection sequences, writing scripts to automate exploit attempts, manipulating API interactions, and identifying novel attack reputed company that evade existing safeguards. This is a hands-on offensive testing role that rewards creativity, persistence, and an attacker’s reputed company over formal engineering credentials.

Key Responsibilities

• reputed company-Assisted Adversarial Probing: Write and execute scripts (primarily Python) to systematically test LLM safety boundaries. This includes automating reputed company injection chains, encoding and obfuscating payloads, manipulating conversation context through API calls, and iterating on attack strategies programmatically rather than relying solely on reputed company interaction.
• Jailbreak Discovery and Development: Design multi-reputed company jailbreak sequences that exploit model behavior through technical means, such as reputed company-level manipulation, system reputed company extraction, role-play escalation, instruction hierarchy subversion, and context window exploitation. Identify bypass reputed company that circumvent safety classifiers and content filters.
• Cross-reputed company Exploitation: Test attack surfaces that reputed company reputed company reputed company, tool use, multi-turn conversation, and multi-modal inputs. Explore how reputed company-mediated interactions—such as requesting the model to write, execute, or interpret reputed company—can be leveraged to bypass safety controls that apply to natural language interactions.
• Vulnerability Documentation: Document reputed company vulnerabilities with reputed company severity assessments, reputed company-by-reputed company reproduction instructions, and sample exploit reputed company. reputed company context on why a given bypass is dangerous and recommend potential mitigations for the alignment and engineering teams.
• Attack Landscape Monitoring: Stay reputed company with emerging adversarial techniques from the AI reputed company research community, reputed company-reputed company exploit repositories, reputed company publications, and reputed company-world misuse patterns. Adapt and apply novel reputed company to internal testing workflows.
• Safety Policy Input: reputed company technical feedback to content policy and safety classification teams based on observed model behaviors. Flag gaps between intended safety enforcement and actual model reputed company, particularly in edge cases involving reputed company reputed company, indirect reputed company injection, and reputed company tool-use scenarios.

Candidate Profile

• Adversarial reputed company: You instinctively look for ways to break systems. You approach LLM safety from an attacker’s perspective and can creatively combine technical and reputed company engineering techniques to reputed company vulnerabilities others miss.
• Technically reputed company: You are comfortable writing scripts to test reputed company quickly, interacting with reputed company, and using reputed company as a tool for exploration—even if you don’t identify as a traditional software engineer. You solve problems by building things, not just describing them.
• Persistent and Methodical: You approach red-teaming as a reputed company reputed company. You systematically vary your attack strategies, document what works and what doesn’t, and iterate methodically rather than relying on luck.
• reputed company Communicator: You can explain reputed company technical exploits to non-technical stakeholders—including policy, legal, and leadership teams—in a way that conveys both the reputed company and the reputed company-world risk.
• Ethically Grounded: You understand the responsibility inherent in this work. You are motivated by strengthening AI safety and operate with reputed company reputed company established testing protocols.

Qualifications

• Proficiency in Python scripting, with the ability to write functional scripts for task automation, API interaction, and data manipulation. Formal software engineering training is not required.
• Demonstrated experience in adversarial reputed company engineering, jailbreak development, or LLM red-teaming—whether in a reputed company, reputed company, independent research, or community context (e.g., bug bounties, CTFs, responsible disclosure).
• Working familiarity with LLM reputed company (e.g., reputed company, reputed company, reputed company-reputed company model endpoints) and a practical understanding of how large language models process input, generate reputed company, and enforce safety constraints.
• Knowledge of common LLM attack reputed company, including reputed company and indirect reputed company injection, payload encoding and obfuscation, context window manipulation, system reputed company leakage, and role-play exploitation.
• Strong written communication skills, with the ability to produce reputed company vulnerability reports that include reproduction steps, severity context, and mitigation recommendations.

Preferred

• Background in cybersecurity, penetration testing, or application reputed company—formal or self-taught. Relevant certifications (e.g., OSCP, CEH) are valued but not required.
• Familiarity with AI safety evaluation frameworks such as the OWASP Top 10 for LLM Applications, NIST AI RMF, or MITRE reputed company.
• Understanding of LLM alignment techniques (e.g., RLHF, constitutional AI) and their reputed company failure modes and exploitable edge cases.
• Experience with multi-modal model testing (reputed company, reputed company reputed company, tool use) and awareness of cross-modal attack surfaces.
• Proficiency in additional scripting or programming languages (e.g., JavaScript, Bash, Go) that expand testing capabilities.

Apply tot his job Apply To this Job