Jobs at Alice (Formerly ActiveFence)

Adversarially test and harden generative AI models against cyber-enabled CBRNE threats by designing prompts, jailbreaks, multi-turn attack scenarios, and evaluation rubrics; develop red-team test suites, document failure modes, reproduce findings, and provide actionable mitigations to AI safety and model-alignment teams.

Perform adversarial red-teaming and risk evaluations of generative AI to identify biological dual-use risks, translate biosafety/regulatory standards into model safety requirements, and advise AI safety teams while monitoring emerging biosecurity threats and updating benchmarks.

Evaluate and strengthen Generative AI safety guardrails for chemical content through adversarial red-teaming, taxonomy audits, prompt research, and risk reporting aligned with chemical regulations and standards.

Perform static and dynamic Android malware analysis and reverse engineering; detect and document emerging Android malware trends; write detection rules and automation; collaborate cross-team and produce threat intelligence reports.

Research and analyze fraud detection mechanisms, abuse vectors, and platform vulnerabilities across web and mobile. Conduct OSINT/WEBINT investigations, build and operate research tooling and environments, analyze telemetry and datasets, automate research workflows, simulate abuse scenarios, monitor malicious channels, and produce actionable intelligence and mitigation recommendations.

Investigate and analyze fraud across web and mobile platforms using OSINT/WEBINT; identify tactics, vulnerabilities, and patterns in large datasets; monitor third-party channels and dark web; produce detailed reports with actionable mitigation recommendations.

Perform OSINT/WebINT investigations across websites, forums, and messaging platforms; monitor malicious activity; assess content policy suitability for vulnerable audiences; produce reports and actionable insights; support product and intelligence teams; analyze large datasets.

Research and analyze deep and dark web sources to assess threat actors and TTPs, produce technical intelligence reports for clients, collaborate with team leads and stakeholders, review and enrich analyst outputs, and maintain analytical procedures and security measures.

Serve as strategic HR advisor for the London office, partnering with leaders on talent management, workforce planning, people analytics, performance and engagement; ensure UK and US compliance, support hiring, build office culture, and execute HR programs to scale the site.

Conduct advanced OSINT and data mining across the surface and deep web to analyze mobile threats. Monitor forums, messaging channels, and dark web communities; extract large datasets; apply statistical, scripting, and AI techniques; translate findings into technical intelligence reports and actionable detection/enforcement recommendations; collaborate with technical teams to automate data collection and build lightweight tools.