Top Tech Jobs & Startup Jobs

Adversarially test and harden Generative AI models against cyber-enabled CBRNE threats by designing and executing red-team prompts, jailbreaks, multi-turn attack scenarios, and model evaluations. Create realistic cyber-CBRNE attack scenarios involving ICS/OT and critical infrastructure, document failure modes, reproduce findings, and provide actionable mitigations. Develop test suites, adversarial datasets, evaluation rubrics, and risk taxonomies while keeping current on GenAI attack techniques and CBRNE security risks.

Assess and strengthen safety guardrails for Generative AI handling chemical information via adversarial red-teaming, taxonomy audits, model evaluation, and regulatory alignment. Identify dual-use risks, prevent material enablement of chemical harms, maintain knowledge of chemical conventions and controls, and communicate technical findings to safety teams.

Own top-of-funnel outbound and inbound prospecting to generate qualified meetings with frontier AI labs, GenAI-native companies, and hyperscalers. Build outreach sequences, cold call and email prospects, collaborate with Account Executives, and refine playbooks and sales processes to drive pipeline and conversions.

Own full sales cycle for GenAI customers, engaging senior product, research, and safety stakeholders. Position and sell AI safety, red teaming, model evaluation, and post-training data services. Scope pre-sales, shape proposals with solutions teams, drive pricing and negotiations, and maintain accurate pipeline forecasting.

Lead AI safety role developing adversarial prompt strategies, owning end-to-end projects, mentoring junior analysts, managing multilingual abuse datasets, researching circumvention tactics, and partnering with engineering, product, and policy teams to secure generative AI models.

Lead a multidisciplinary red teaming team to design and run adversarial tests, evaluate model risks, produce high-quality deliverables, and communicate findings to clients while improving methodologies and workflows.

Analyze content infringements and write adversarial prompts to find model vulnerabilities across LLMs, text-to-image/video, and agents. Manage datasets and projects end-to-end, investigate evasion tactics, collaborate with engineering, product, and policy teams, and promote knowledge sharing to improve model safety.