You want to operate at the cutting edge of AI, leading groundbreaking developments in AI safety and security for global impact. As a Lead Research Engineer at Lakera, you will be at the forefront of the implementation of LLMs and LLM security. Stress-testing the rapidly shifting technology, you'll conceive and build defensive mechanisms to protect against an ever-evolving threat landscape. You want to work on solutions that enable millions of developers to build the future securely. Your work will play a vital role in ensuring that AI can unleash its best potential–for good.
About LakeraLakera is on a mission to secure the era of intelligent compute. We are heading towards a future where AI-powered applications take center stage. Here at Lakera, we're not just dreaming about the future; we're building the security foundation for it. We empower builders, giving them the confidence to navigate this new dynamic landscape and unleash the next phase of innovation.
We work with Fortune 500 companies, startups, and foundation model providers to protect them and their users from adversarial misalignment. We are also the company behind Gandalf, the world’s most popular CTF. If you're eager to be part of a team that's not just keeping pace but setting the pace, Lakera is the right place for you. Let's shape the future together.
Projects You Could Be Working On

• Red-teaming of LLMs: design and implement offensive security techniques to find vulnerabilities in LLMs and how to exploit them.
• Build defense models to guard LLMs from prompt injection attacks, prevent data leakage, hallucinations and more.
• Investigate possible exploits for a multi-agent system containing multiple LLMs communicating with external APIs and interacting with one another.
• Reinvent our existing defenses: can you maintain performance but make them 100 times faster?

About You

• You've been a key contributor in at least one major project (academic or industrial) that significantly influenced the recent advancements in transformer-based architectures.
• You thrive on translating your ideas into tangible products with wide reach.
• You aspire to play a pivotal role in defining the future of secure AI within a mission-driven company with ambitious goals.

Location: San Francisco.
Logistics: Location-based hybrid policy: Currently, we would like staff to be in the office 2 - 3 days a week.
Deadline to apply: None. Applications will be reviewed on a rolling basis
Compensation and Benefits: Our compensation package consists of three elements: salary, equity, and benefits.
We are committed to paying fairly and aim for these three elements collectively to be highly competitive with market rates. Equity - On top of this position's compensation, equity will be a major component of the total compensation. We aim to offer higher-than-average equity compensation for a company of our size and communicate equity amounts at the time of offer issuance.
Benefits

• Equity package.
• Comprehensive health, dental, and vision insurance.
• 401k plan with employer matching of 100% of employees contributions up to 3% of pay.
• 12 weeks of paid parental leave.
• Unlimited PTO.
• Headspace Membership.
• Work equipment (laptop, computer screen, etc).
• Stipends for education, home office improvements, commuting, and wellness.
• Daily lunches and snacks in our office.
• Relocation support for those moving to the Bay Area.

🔗 Join us on Momentum, the slack community for AI Safety and Security everything.
To remove your information from our recruitment database, please email privacy@lakera.ai