AI Security Researcher/Research Engineer at Brave

<p><strong>AI Security Researcher / Research Engineer</strong></p> <p><strong>Remote or hybrid - London preferred but North America, EU, UK accepted</strong></p> <h3><strong>About Brave:</strong></h3> <p>Brave is on a mission to protect the human right to privacy online. We’ve built a free web browser that blocks creepy ads and trackers by default, a private search engine with a <em>truly</em> independent index, private AI assistant, latest privacy and security features, and a private ad network (opt-in!) that directly rewards you for your attention. Already over 120 million people regularly use Brave for a faster, more private web. Millions more switch every month.</p> <p>The internet is a sea of ads, hackers, and echo chambers. Big Tech makes huge profits off our data, and tells us what’s true and what’s not. Brave is fighting back. Join us!</p> <h3><strong>Summary</strong></h3> <p>We are looking for a researcher/research engineer to help mitigate the security risks that come with building AI systems-especially LLM-powered web agents and chatbots. In this role, you'll design and implement secure-by-design architectures, audit our LLM-powered web agent (https://brave.com/blog/ai-browsing/) and chatbot, and help set Brave's direction on how we identify, measure, and reduce security risk across AI products.</p> <h3><strong>Responsibilities</strong>&nbsp;</h3> <ul> <li>Design and execute adversarial evaluations to uncover failure modes in LLM-powered web agents and chatbots (e.g., prompt injection, tool abuse, data exfiltration)</li> <li>Analyze model behavior (including internal thoughts) to understand and forecast security risks in frontier models</li> <li>Develop and prototype security-focused training and fine-tuning techniques&nbsp;</li> <li>Augment web agents with security principles including information flow control, privilege control and contextual security</li> <li>Partner with engineers and (privacy, ML, and Cryptographic) researchers to translate findings into product changes, tests, and measurable security improvements</li> <li>Help define a forward-looking security strategy and policy for building and responsibly releasing web agents—advocating for user protection</li> </ul> <h3><strong>You may be a good fit if you have</strong></h3> <ul> <li>Demonstrated experience working on Secure AI (prompt injection attacks and security guardrails)</li> <li>Strong publication record in AI security, ML security, or closely related areas</li> <li>A track record of shipping products and features inside a fast-moving environment</li> <li>Strong coding skills in Python and familiarity with ML frameworks like PyTorch or JAX</li> <li>Experience training, fine-tuning, and evaluating large language models</li> <li>Deep familiarity with large language models and web agents, how they work, and how they are trained</li> <li>Experience applying security principles (e.g., information flow control, access control/least privilege)</li> <li>Demonstrated success in bringing clarity and ownership to ambiguous technical problems</li> <li>A Ph.D. in computer science is highly preferred, but we may consider some exceptions with industry experience</li> </ul> <h3><strong>Skills That Will Set You Apart from the Competition</strong></h3> <ul> <li>Knowledge of AI Systems (pipelines, security evaluation, etc.)</li> <li>Open source projects on security/privacy</li> <li>Experience with confidential computing and ZKP/SMPC protocols</li> <li>Ph.D. in computer science from a top-tier school</li> <li>A strong publication record in premier systems, performance, or ML&nbsp;</li> <li>Work experience in industry is desirable</li> </ul> <h3><strong>Working at Brave - What we offer</strong></h3> <ul> <li>Ability to work at an exciting and well-funded international startup headquartered in San Francisco</li> <li>Cutting-edge technology, allowing you to work with state-of-the-art tools and software solutions</li> <li>Competitive compensation and plenty of room for personal growth</li> <li>Great international exposure and team atmosphere</li> </ul> <p>We are looking to hire in London but would <em>consider</em> an exceptional candidate in the rest of Europe.&nbsp;</p> <p>NO AGENCIES or RECRUITERS PLEASE - Unfortunately, we cannot work with third parties on these searches.</p> <p><br><br></p>