Department: Intelligence
Location: Remote
Employment Type: Full-time
As a GenAI Chemical Safety Expert, you will play a critical role in evaluating and strengthening the safety guardrails of Generative AI systems handling chemical information. You will combine deep subject-matter expertise in the chemical sciences with hands-on prompt research, red-teaming, and model pairing to identify dual-use risks, prevent the material enablement of chemical harms, and ensure AI outputs adhere to strict chemical safety and regulatory standards.
Execute rigorous adversarial red-teaming and comprehensive taxonomy audits to uncover latent model vulnerabilities, meticulously scrutinizing AI-generated content for toxicological precision, dual-use implications, and clandestine synthesis protocols to deliver high-fidelity, actionable intelligence to safety teams.
Maintain up-to-date knowledge on international chemical conventions, precursor controls, and industrial safety standards.
Location: Must be located in and authorized to work within the United States (excluding Illinois and Texas).
Education: Ph.D. in Organic Chemistry, Analytical Chemistry, Chemical Engineering, Toxicology, Materials Science, or a related chemical science (Master's degree with 5+ years of experience considered).
Subject-Matter Expertise: Deep understanding of reaction mechanisms, chemical synthesis, toxicological risk, and chemical security standards.
AI Safety Aptitude: Comfort and experience with hands-on prompt research, adversarial prompt generation, and evaluating model output safety.
Critical Analysis: Ability to spot subtle evasive phrasing, chemical pseudonym usage, or step-by-step synthesis instructions embedded in seemingly benign queries.
Communication: Strong technical writing skills to document findings, rank risk severities, and inform alignment decisions.
Knowledge of AI prompt engineering concepts and practices, including adversarial prompt writing
Familiarity with frontier AI safety benchmarks, evaluation frameworks, and ethical guidelines for GenAI.
Expertise in one or more of the following chemical risk areas:
Salary range: $150,000 - $178,000. Range may vary based on experience. Salary at the time of offer will be commensurate with experience.
Alice.io, formerly known as ActiveFence, is a trust, safety, and security company specializing in safeguarding artificial intelligence systems across their entire lifecycle. The company focuses on identifying and mitigating risks in generative AI through domain expertise in Chemical, Biological, Radiological, and Nuclear (CBRN) areas. Alice.io offers coverage and security solutions designed to address the emerging challenges posed by AI technologies. The company operates an 'Elite Collective' model, engaging specialized experts on a project-based, on-demand basis to conduct high-impact interventions for sophisticated technology challenges.