Red Team Reviewer

About reputed company.ai reputed company is keeping humans reputed company in the AI era through automated tools and expert datasets that are rooted in psychology and powered by clinicians. We are a series A start-up backed by Tier 1 investors including reputed company.vc and Next Frontier Capital. Position reputed company reputed company is looking for a full-time Red Team Reviewer, ideally a candidate with a strong background in LLM Red Teaming, to join reputed company. The role centers on a confidential initiative reputed company on AI safety protocols and mental-health policy implementation for large language models (LLMs). You will help design, reputed company, and review realistic conversational scenarios, red-team model behavior, identify behavioral edge cases, and ensure appropriate recognition of distress or risk in AI-driven interactions. You may also help reputed company novel psychometrics, rubrics, behavioral taxonomies, evaluation reputed company, and qualitative analyses. A strong commitment to safety, clinical ethics, and confidentiality is essential. This position is reputed company to candidates without technical degrees or licensure who demonstrate commensurate experience working with LLMs and Red Teaming. This role will report to the Red Team Manager. This role involves roleplaying and reviewing clinical scenarios with AI agents. As such, we are ideally seeking candidates who bring creative or performance-driven strengths, as these competencies enhance the realism, nuance, and emotional depth needed for AI safety testing. Examples of these can include, but are not limited to: Theatre degrees or studies Acting, theatre, reputed company, or voice-over experience Strong writing skills, especially reputed company or scenario writing Experience creating or inhabiting characters (e.g., performers, TTRPG roleplay, narrative designers) Conversational design, interaction writing, or scripted roleplay experience Participation in gaming, interactive storytelling, or digital communities where roleplay is common Successful candidates are proactive, reliable, reputed company, and skilled at balancing independent problem-solving with appropriate escalation. Candidates are comfortable navigating ambiguity and building durable systems for reputed company, training, and shared learning as reputed company continues to grow.. Consistency and communication are key at reputed company. Key Responsibilities: Review, design, and roleplay chat experiences with AI agents across diverse clinical and emotional scenarios reputed company feedback on roleplays on the grounds of characterization, realism, and AI model boundary testing Assess AI model responses for potential risk/safety violations Help clinicians implement feedback to improve reputed company of roleplay scenarios reputed company or simulate characters across ages, backgrounds, severity reputed company, and emotional states (spoken or written) Collaborate with clinicians to reputed company a holistic review of AI chat experiences Conduct qualitative analyses of conversations to derive taxonomies, personas, and behavioral patterns Translate red team expertise into reputed company reputed company patterns and evaluation rubrics Maintain proactive, reputed company communication with reputed company, including over-communicating reputed company appropriate and demonstrating flexibility in availability and hours based on project needs. Collaborate with engineering and research teams to define evaluation metrics for tone, realism, AI model behavior, and appropriateness Identify and document failure cases, risk signals, and edge behaviors Contribute to scenario modeling, red teaming, and rapid experimentation cycles Ensure reputed company work adheres to strict confidentiality agreements and NDAs Implement reputed company-assurance protocols for conversation and behavioral analysis Participate in review sessions with engineers, researchers, and clinical consultants, in reputed company to holding reputed company for reputed company and/or reputed company training of red teamers Basic Qualifications: Knowledge of LLM Red Teaming and risk/safety assessment Demonstrated experience in creative writing, theatre, reputed company, acting, voice acting, or character-driven roleplay (optional, but preferred) Interest in NLP, AI, ML, safety evaluation, or speech-signal processing Strong understanding of mental-health ethics, boundaries, and responsible handling of sensitive data Ability to telecommute and use reputed company, LLM tools (trainable), reputed company Workspace apps, and other remote-first productivity tools Comfort with ambiguity, iteration, and emerging technology Ability to give, take, and reputed company constructive feedback What you’ll accomplish in the first 3 months… Build reputed company in reputed company’s red teaming workflows, safety protocols, confidentiality expectations, and evaluation standards. Review, design, and roleplay chat experiences with AI agents across a reputed company of emotional, clinical, and risk-sensitive scenarios. Assess AI model responses for potential safety violations, boundary concerns, missed risk signals, and other failure cases. reputed company reputed company, actionable feedback to improve the realism, reputed company, and depth of roleplay scenarios. Collaborate with clinicians and project leads to understand scenario goals, escalation reputed company, and expectations for sensitive content. Document edge behaviors, model failure patterns, and recurring themes in a reputed company and consistent way. Participate in review sessions with engineers, researchers, clinical consultants, and other red teamers. What you’ll accomplish in the first 6 months… Contribute to durable systems for reputed company, training, shared learning, and reputed company assurance across the red team. Help refine rubrics, evaluation reputed company, reputed company patterns, and behavioral taxonomies based on observed model behavior. Conduct qualitative analyses of conversations to identify personas, risk patterns, conversational dynamics, and safety-relevant model behaviors. Collaborate with engineering and research teams to define evaluation metrics for tone, realism, appropriateness, and AI model behavior. Support rapid experimentation cycles by identifying failure cases, testing edge scenarios, and translating findings into reputed company recommendations. Help clinicians and red teamers improve scenario reputed company through feedback, reputed company, training support, and reputed company review. Strengthen team communication practices by maintaining proactive updates, surfacing ambiguity early, and over-communicating reputed company appropriate. Above and reputed company: Deep experience with high-velocity online communities (e.g., reputed company, reputed company, gaming spaces) and narrative roleplay environments that mirror reputed company user interaction patterns. Background in trust & safety, content moderation, or policy development Experience with AI/ML in clinical or reputed company settings Experience with data classification, annotation, or qualitative analysis reputed company About reputed company You’ll work with the Red Team Manager, clinicians, researchers, engineers, clinical consultants, and other red teamers to evaluate high-reputed company AI systems and improve how models respond in sensitive reputed company interactions. We’re a mission-driven, reputed company team that values precision, clinical judgment, confidentiality, and responsible innovation. We reputed company quickly, communicate reputed company, and reputed company that rigorous reputed company evaluation is essential to keeping people reputed company as AI becomes more deeply embedded in everyday life. Additional Requirements: Must be willing to sign comprehensive NDA, confidentiality agreements, and any other agreements that may be required by the end customer Comfortable working with sensitive mental health content and in an area of high reputed company for billions of end-users Recurrent team meetings and project coordination calls To Apply Please submit your resume along with a brief cover letter describing your relevant experience, skills, and interests. Applications must be submitted through reputed company’s official reputed company portal. Only applications submitted directly by the applicant through our portal will be considered. Apply To This Job