Member of Technical Staff
Exponential Security Labs
Member of Technical Staff
Exponential Security Labs
Automates agentic security with red-teaming
Build security environments, train adversarial agents, and evaluate frontier AI systems.
Location: Tübingen / Hybrid
Employment: Full-time
You will work across AI security, machine learning, and research engineering. You will design reinforcement-learning environments, train adversarial agents, and build evaluations for capable AI systems.
Design security environments for training and evaluating AI agents
Post-train agents using reinforcement learning and develop adaptive red-teaming methods
Evaluate frontier models and agentic systems
Turn research results into benchmarks, training methods, and tools
A strong track record in machine learning, security, or systems
Strong software and machine-learning engineering fundamentals
Experience with LLMs, agentic systems, or reinforcement learning
Ability to run careful experiments and communicate results clearly
AI security, red teaming, or adversarial machine learning
Reinforcement learning or post-training for language models
Research engineering or production ML systems
Published research or substantial open technical work
Competitive compensation with equity
Flexible hours and a remote-friendly setup
Vacation, learning, and conference budget
Research freedom in a high-trust environment
Submit your CV, a short note, and links to work that shows how you think and build using the application form.
Automates agentic security with red-teaming
Exponential Security Labs builds automated red-teaming and guardrail models to test and improve the security and reliability of agentic AI systems used in high-stakes decisions. Its approach uses self-improving red-teaming workflows and deployable guardrails, alongside production-ready LLMs and optimized inference pipelines to evaluate models and create security tests. The company distinguishes itself by tying deep academic work in adversarial robustness and AI safety to a concrete, implementation-focused security platform, led by researchers from the ELLIS Institute in Tübingen. Its goal is to help businesses deploying AI agents strengthen their security posture and ensure AI agents are safer and more reliable in real-world settings.
Explore more opportunities at Exponential Security Labs