Senior / Staff ML Engineer, AI Security (Runtime Defenses)
- Full-time
- Referral Category: Golden Position
- CP Department: AI Agent Security
- Office Location: Hardturmstrasse, Zurich, Switzerland
- Career site Category: R&D
Company Description
At Check Point, what you do matters. Every day, we protect over 100,000 organizations worldwide from increasingly sophisticated cyber and AI-driven threats, securing their AI transformation.
Our prevention-first approach safeguards hybrid networks, cloud environments, digital workspaces, and AI systems, stopping attacks before they happen.
This is where innovation meets real-world impact. You’ll help customers across industries operate with confidence in a rapidly changing digital world, working alongside smart, curious people who take ownership, challenge assumptions, and solve complex problems.
We’re proud to be recognized by TIME, Newsweek, and Forbes for excellence and workplace culture.
What really sets Check Point apart is the opportunity to grow, contribute, and help companies navigate their AI transformation securely.
If you’re excited to work at the forefront of AI-driven security on a global scale, this is the place to do it
Job Description
Securing generative AI systems and agents is one of the most important problems of our generation, and Check Point Zurich (formerly Lakera) is one of the key players in shaping the field. We crowdsource adversarial attacks through gamification, define benchmarks, and publish what we learn to help the industry. We turn that knowledge into enterprise-grade protection; our customers, ranging from fast-moving AI-native companies to regulated enterprises, face the same challenges: the upside of enabling AI for coding, deploying agents to production, mixing sensitive and untrusted data is not possible without the right security measures.
We are hiring for two teams. Runtime Defenses builds the ML systems behind our protection, from training data to runtime inference. Red Team builds the product that generates attacks, evaluates, and stress tests our customers’ agents. Both work closely with multiple, full-time product managers who have deep ML and security backgrounds, and with an in-house research team. We stay close to customers, and we experiment a lot, always with a pragmatic focus on what improves the product.
What you will do
- Own problems end to end in a product area that is still taking shape: define what to build, ship it, and improve it in production
- Build the data, evals, and models that determine how well our products work, with a focus on LLMs and NLP
- Own customer outcomes: work with customers on integration and evaluation, follow how our products perform in production, and fix what falls short
- Work closely with Product and Research to turn what we learn from customers and the field into the roadmap
- Raise the technical bar through design reviews, mentoring, and leading by example
Qualifications
Who you are
- You have built and shipped ML systems to production. We are open on experience: Senior typically means 5+ years and Staff 8+, with the scope of past work counting more than years
- You have strong data and quality skills: building datasets, defining evals, and finding and fixing failure modes
- You have hands-on experience with language models / NLP. We also welcome strong candidates from other ML domains with a track record in data and quality
- You are curious about AI Security as a problem and a space, and you want to achieve pioneering results in it
- You take responsibility for customer success and like working with customers directly. Experience owning a customer-facing problem, such as an integration, is a plus
- Cyber security background is welcome, but not required
Why you’ll like it here
- Talented team. Our engineers combine strong ML skills with low ego, a habit of helping each other, and real curiosity about product and customers
- Frontier technology. You work with state-of-the-art models, LLMs, and agents in a field that moves fast. The problems are hard and open, and side experiments can change the roadmap
- Learning from production. We own the product end to end, so we see how customers use it at the leading edge of AI adoption, and that shapes what we build next. New engineers ship to production quickly
Example projects you would be working on
- Develop methods to inspect traffic through an AI Gateway from security perspective;
- Build attack pipelines to demonstrate vulnerability exploitation in complex agentic systems;
- Solve the problem of running untrusted open weight models securely;
- Mine new attack techniques from the logs of the agent-breaker game;
- Unblock the usage of coding agents via monitoring/steering, in a harness- and model-agnostic way.
By clicking the link above or any third-party link within this posting, you are leaving this site and going to a third-party website where the third-party website's terms and privacy policy apply