Senior Security Researcher
ActiveFence
Posted
Jan 21, 2026
Location
Remote
Type
Full-time
Mission
What you will drive
INNOVATE UNAFRAID
Security, Safety, and Trust
for the AI Era
Build, run, and keep communicative tech safe for your users at every touchpoint - including GenAI apps, UGC platforms, and whatever comes next, by leveraging the world’s deepest adversarial intelligence dataset.
Get a DemoTrusted by the world’s biggest enterprises & foundation model labs
Alice Data Advantage
Alice is the world’s largest collector and manager of adversarial intelligence data. Our data is the cornerstone for protecting platform, tech, and users online.
Learn More >
Safeguarding more than 50% of the world’s online experiences
3B+
Users
120+
Languages
1B+
Daily AI-Human interactions
From UGC to GenAI and humanoid robots, Alice allows you and your users to advance unafraid.
Epic, Real-World
Adversarial Intelligence
Our solutions outperform industry benchmarks because they're powered by data drawn from a decade of real-world adversarial research, enabling you to act before abuse becomes news.
The Rabbit Hole
Data Moat
With billions of continually updated toxic examples, we train sharper classifiers and fuel stronger red-teaming, giving you unmatched accuracy and coverage.
Adaptive, Customizable
Policy Alignment
Keep your policies front and center, tuning coverage to your regulatory needs and risk tolerance - across every modality, so each interaction stays trusted and aligned.
The internet is a wonderful place. Mostly.
Wherever people and technology meet, powerful tools can be manipulated to do harmful things. And you’re held accountable.
Unintended GenAI Behavior
GenAI can produce harmful or misleading content at a scale traditional security and safety controls can’t reliably manage.
Application-Level Exploitation
Prompt injection, jailbreaks, and model exploits expose applications, agents, and integrations to data leakage or abuse.
Governance and Compliance Gaps
Abusive, harmful, or non-compliant interactions undermine security and safety policy enforcement and responsible AI governance.
Reputational and Trust Exposure
A single failure can trigger legal liability, regulatory scrutiny, stalled innovation momentum, and lasting damage to brand trust.
Step into GenAI Wonderland
Introducing
WonderSuite
Powered by Adversarial Intelligence. Built for Secure, Trusted Enterprise AI.
Platform OverviewWonderBuildPre-Launch Stress-Testing
Prepare your AI models, apps, and agents for responsible, resilient, confident deployment
WonderFenceDynamic Runtime Guardrails
Keep live apps and agents safe, secure, and aligned with your policies and brand
WonderCheckOngoing Automated Red-Teaming
Evaluation for production AI systems to detect drift, surface emerging risks, and prioritize remediation
If you’ve talked online with a friend, colleague, or chatbot in the last hour, Alice likely protected you.
PROTECTING 3B+ PEOPLE ONLINE
Powered by the world’s most comprehensive adversarial intelligence engine -
Rabbit Hole
Alice is powered by Rabbit Hole, built on billions of toxic, manipulative, and abusive data samples and cross-cultural expert analysis. Rabbit Hole adapts in real time, foreseeing emerging threats, surfacing unseen risks, and feeding guardrails, enabling Alice to test, harden, and protect systems of every kind: from UGC to GenAI and soon enough, humanoid robots.
It’s what enables us to protect half the world’s online users from harm, and why leading technology companies and frontier model labs rely on Alice at scale.
Navigate GenAI Wonderland
"Alice has significantly impacted our iteration speed and confidence in our evaluations and mitigations. It has enabled us to develop a faster evaluation suite, allowing us to release models more quickly and safely."
Seraphina Goldfarb-TarrantHead of AI Safety
"Alice has been a great partner to work with & I look forward to delivering next editions of Nova models to delight customers, while raising the bar on safety."
Rahul GuptaSenior Manager, Responsible AI
"Alice is the only vendor I've seen that does this type of extremely high quality safety work based in a deep understanding of threat actors across violation types."
Head of SafetyLeading LLM
Proven peace of mind
Trusted
The backbone of the internet’s most popular platforms, proven at scale across 100+ languages, keeping over 3 billion people protected.
Safe
Powered by the industry’s richest real-world intelligence dataset, intercepting tens of millions of adversarial sources, delivering unmatched safety coverage.
Secured
Protecting and fortifying GenAI applications, agents, and models against evolving exploit and abuse techniques. Tune defenses to your needs and innovate with confidence.
Safe. Honest. Kind.
What’s New from Alice
Securing Agentic AI: Meeting the 2026 Federal Assurance Bar
Learn how the FY2026 NDAA and new NIST frameworks are shifting agentic AI from experimental to regulated. Master the security controls and Zero Trust principles required to win federal AI contracts this year.
Learn MoreWe Audited the OpenClaw Marketplace. We Found a Trojan.
A malicious “Skill” for the OpenClaw AI framework, titled “RememberAll”, is currently being distributed via the ClawHub marketplace. While purporting to be a personal reminder utility, the skill contains hidden instructions to download a secondary payload (secure-sync) that harvests sensitive credentials (API keys, .env files) and exfiltrates them to a public ntfy.sh dead-drop resolver.
Learn MoreThe Art of the Unseen: Why We Built Caterpillar
Learn how to secure your AI agent ecosystem with Caterpillar, a free open-source tool designed to unmask hidden vulnerabilities, injection paths, and unsafe configurations in AI skills.
Learn More
About
Inside ActiveFence
ActiveFence provides tools for managing Trust & Safety operations on online platforms.