AI Safety Consultant

About the role

We’re partnering with this company to present an exciting opportunity for a hands-on applied researcher focused on identifying, measuring, and reducing safety risks in conversational and agentic AI products. This position is ideal for someone who can turn ambiguous safety challenges into practical evaluations, mitigations, and monitoring systems that help protect users while supporting product innovation.

Responsibilities

• Develop product-specific threat models and harm taxonomies for conversational, recommender, and tool-using AI systems.
• Design and run single- and multi-turn adversarial evaluations using expert red teaming, automated attack generation, synthetic data, and sampled production data.
• Build reusable Python evaluation pipelines, LLM-as-a-judge workflows, regression tests, dashboards, and curated golden datasets.
• Validate evaluators against human labels and translate findings into mitigations, monitoring improvements, and actionable stakeholder recommendations.

Requirements

• Must work in EST time zone.
• 3+ years of experience delivering safety evaluations or mitigations for a real AI or machine-learning product, with automation used to scale the work.
• 5+ years of experience working for enterprise technology companies
• Basic programming skills in Python and advanced SQL for data analysis are required.
• Experience designing adversarial tests, evaluation datasets, taxonomies, rubrics, and metrics.
• Ability to work autonomously when the risk, success criteria, and methodology are initially unclear.
• Experience working across research, engineering, product, policy, or Trust & Safety.
• Clear written communication and a record of turning research findings into action.