GenAI Security - Principal Security Research Engineer

About this role

<div class="content-intro"><p>Elastic, the Search AI Company, enables everyone to find the answers they need in real time, using all their data, at scale — unleashing the potential of businesses and people. The Elastic Search AI Platform, used by more than 50% of the Fortune 500, brings together the precision of search and the intelligence of AI to enable everyone to accelerate the results that matter. By taking advantage of all structured and unstructured data — securing and protecting private information more effectively — Elastic’s complete, cloud-based solutions for search, security, and observability help organizations deliver on the promise of AI.</p></div><h3><strong>What is The Role</strong></h3> <div class="p" data-block="true" data-editor="drfgl" data-offset-key="bi82b-0-0"> <div class="public-DraftStyleDefault-block public-DraftStyleDefault-ltr" data-offset-key="bi82b-0-0"> <div class="p" data-block="true" data-editor="b5ec8" data-offset-key="bi82b-0-0"> <div class="public-DraftStyleDefault-block public-DraftStyleDefault-ltr" data-offset-key="bi82b-0-0"> <div class="p" data-block="true" data-editor="ca6k3" data-offset-key="bi82b-0-0"> <div class="public-DraftStyleDefault-block public-DraftStyleDefault-ltr" data-offset-key="bi82b-0-0"><span data-offset-key="bi82b-0-0"><span data-text="true">As a Principal Security Research Engineer on the Threat Research and Detection Engineering (TRaDE) team, you'll play a key role in shaping the detection capabilities of Elastic Security. You'll work hands-on with detection engineering and threat research, focusing on enhancing our defenses, particularly in the areas of AI security. This position invites you to apply your solid security background and keen interest in offensive security validating detection methods, helping to create effective and reliable detection content that benefits the wider community.</span></span></div> </div> <h3 class="public-DraftStyleDefault-block public-DraftStyleDefault-ltr" data-offset-key="3m9da-0-0"><span data-offset-key="3m9da-0-0"><span data-text="true">What You Will Be Doing</span></span></h3> <ul class="public-DraftStyleDefault-ul" data-offset-key="6714c-0-0"> <li class="public-DraftStyleDefault-unorderedListItem public-DraftStyleDefault-reset public-DraftStyleDefault-depth0 public-DraftStyleDefault-listLTR" data-block="true" data-editor="ca6k3" data-offset-key="6714c-0-0"> <div class="public-DraftStyleDefault-block public-DraftStyleDefault-ltr" data-offset-key="6714c-0-0"><span data-offset-key="6714c-0-0"><span data-text="true">Design and carry out security tests for GenAI applications, agentic systems, and LLM-backed products. These tests will check for various attack types. They include prompt injection, indirect injection, retrieval poisoning, tool misuse, </span></span><span id="popover-trigger-:ro:" class="chakra-text css-8zk7oi"><span data-offset-key="6714c-1-0"><span data-text="true">sensitive</span></span></span><span data-offset-key="6714c-2-0"><span data-text="true"> data extraction, and unsafe delegation to with the core purpose of building security protections</span></span></div> </li> <li class="public-DraftStyleDefault-unorderedListItem public-DraftStyleDefault-depth0 public-DraftStyleDefault-listLTR" data-block="true" data-editor="ca6k3" data-offset-key="6trj0-0-0"> <div class="public-DraftStyleDefault-block public-DraftStyleDefault-ltr" data-offset-key="6trj0-0-0"><span data-offset-key="6trj0-0-0"><span data-text="true">Investigate new multi-domain threat vectors and attack methodologies to stay ahead of emerging risks and translating these into new security protections (e.g. detection rules)</span></span></div> </li> <li class="public-DraftStyleDefault-unorderedListItem public-DraftStyleDefault-depth0 public-DraftStyleDefault-listLTR" data-block="true" data-editor="ca6k3" data-offset-key="5hj9l-0-0"> <div class="public-DraftStyleDefault-block public-DraftStyleDefault-ltr" data-offset-key="5hj9l-0-0"><span data-offset-key="5hj9l-0-0"><span data-text="true">Create and present findings to enhance team knowledge and community awareness</span></span></div> </li> <li class="public-DraftStyleDefault-unorderedListItem public-DraftStyleDefault-depth0 public-DraftStyleDefault-listLTR" data-block="true" data-editor="ca6k3" data-offset-key="e5s6p-0-0"> <div class="public-DraftStyleDefault-block public-DraftStyleDefault-ltr" data-offset-key="e5s6p-0-0"><span data-offset-key="e5s6p-0-0"><span data-text="true">Apply AI-assisted techniques to expand coverage and accelerate validation. This may include developing new capabilities and Elastic AI workflows to streamline our threat research and detection engineering processes</span></span></div> </li> </ul> <h3 class="public-DraftStyleDefault-block public-DraftStyleDefault-ltr" data-offset-key="a1730-0-0"><span data-offset-key="a1730-0-0"><span data-text="true">What You Bring</span></span></h3> <ul class="public-DraftStyleDefault-ul" data-offset-key="aj9pk-0-0"> <li class="public-DraftStyleDefault-unorderedListItem public-DraftStyleDefault-reset public-DraftStyleDefault-depth0 public-DraftStyleDefault-listLTR" data-block="true" data-editor="ca6k3" data-offset-key="aj9pk-0-0"> <div class="public-DraftStyleDefault-block public-DraftStyleDefault-ltr" data-offset-key="aj9pk-0-0"><span data-offset-key="aj9pk-0-0"><span data-text="true">You should have experience working with endpoint data and understand detection engineering GenAI pitfalls working with existing telemetry </span></span></div> </li> <li class="public-DraftStyleDefault-unorderedListItem public-DraftStyleDefault-depth0 public-DraftStyleDefault-listLTR" data-block="true" data-editor="ca6k3" data-offset-key="7itup-0-0"> <div class="public-DraftStyleDefault-block public-DraftStyleDefault-ltr" data-offset-key="7itup-0-0"><span data-offset-key="7itup-0-0"><span data-text="true">You should have hands-on experience using LLM tools for security testing, research, or daily tasks. You need to understand how LLMs work. This includes context windows, tool use, RAG, and agentic chaining. Knowledge of AI testing tools or frameworks, such as Garak, PyRIT, PromptBench, Inspect AI, or similar (including personal research or experiments) is a plus.</span></span></div> </li> <li class="public-DraftStyleDefault-unorderedListItem public-DraftStyleDefault-depth0 public-DraftStyleDefault-listLTR" data-block="true" data-editor="ca6k3" data-offset-key="3phlp-0-0"> <div class="public-DraftStyleDefault-block public-DraftStyleDefault-ltr" data-offset-key="3phlp-0-0"><span data-offset-key="3phlp-0-0"><span data-text="true">You should have experience using AI-assisted development tools and modern AI/ML frameworks. These tools help you accelerate up feature development. They also help you debug complex systems and optimize existing codebases. You will generate telemetry, conduct threat research, and assist with detection engineering workflows.</span></span></div> </li> <li class="public-DraftStyleDefault-unorderedListItem public-DraftStyleDefault-depth0 public-DraftStyleDefault-listLTR" data-block="true" data-editor="ca6k3" data-offset-key="1r26g-0-0"> <div class="public-DraftStyleDefault-block public-DraftStyleDefault-ltr" data-offset-key="1r26g-0-0"><span data-offset-key="1r26g-0-0"><span data-text="true">Proven ability to seamlessly transition between different projects, codebases, or scrum teams based on dynamic business priorities.</span></span></div> </li> <li class="public-DraftStyleDefault-unorderedListItem public-DraftStyleDefault-depth0 public-DraftStyleDefault-listLTR" data-block="true" data-editor="ca6k3" data-offset-key="ahhmk-0-0"> <div class="public-DraftStyleDefault-block public-DraftStyleDefault-ltr" data-offset-key="ahhmk-0-0"><span data-offset-key="ahhmk-0-0"><span data-text="true">You work autonomously and can drive decisions and results in a distributed team by leveraging asynchronous, direct, and transparent communication.</span></span></div> </li> <li class="public-Dr