{"id":89248,"title":"Member of Technical Staff - AI Security","company":"Exponential Security Labs","city":"Tübingen","region":"Baden-Württemberg","location":"Tübingen, Tübingen, Baden-Württemberg, Germany","work_model":"hybrid","employment_type":"full_time","employment":["full_time"],"roles":["data_science","security"],"visa":"not_mentioned","relocation":"not_mentioned","posted_at":"2026-10-05T13:13:26.918000+00:00","tools":["LLM"],"seniority":"lead","years_experience_min":null,"german_requirement":"not_mentioned","german_level":"unspecified","english_requirement":"required","english_level":"unspecified","team_language":"unknown","confidence":0.4,"method":"rules","language_badge":"Not stated","language_evidence":null,"requirements_snippet":"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 …","url":"https://jobs.ashbyhq.com/exponential/8db41a34-f248-4acc-9ba5-c0b3bd06d64a","source":"ashby","agency":null,"description_text":"Build security environments, train adversarial agents, and evaluate frontier AI systems.\nLocation: Tübingen / Hybrid\nEmployment: Full-time\nThe role\nYou 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.\nWhat you’ll work on\n• Design security environments for training and evaluating AI agents\n• Post-train agents using reinforcement learning and develop adaptive red-teaming methods\n• Evaluate frontier models and agentic systems\n• Turn research results into benchmarks, training methods, and tools\n\nWhat we’re looking for\n• A strong track record in machine learning, security, or systems\n• Strong software and machine-learning engineering fundamentals\n• Experience with LLMs, agentic systems, or reinforcement learning\n• Ability to run careful experiments and communicate results clearly\n\nUseful experience\n• AI security, red teaming, or adversarial machine learning\n• Reinforcement learning or post-training for language models\n• Research engineering or production ML systems\n• Published research or substantial open technical work\n\nWhat we offer\n• Competitive compensation with equity\n• Flexible hours and a remote-friendly setup\n• Vacation, learning, and conference budget\n• Research freedom in a high-trust environment\n\nWork with us\nSubmit your CV, a short note, and links to work that shows how you think and build using the application form.","responsibilities_text":"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.\nWhat you’ll work on\n• Design security environments for training and evaluating AI agents\n• Post-train agents using reinforcement learning and develop adaptive red-teaming methods\n• Evaluate frontier models and agentic systems\n• Turn research results into benchmarks, training methods, and tools","requirements_text":"• A strong track record in machine learning, security, or systems\n• Strong software and machine-learning engineering fundamentals\n• Experience with LLMs, agentic systems, or reinforcement learning\n• Ability to run careful experiments and communicate results clearly\nUseful experience\n• AI security, red teaming, or adversarial machine learning\n• Reinforcement learning or post-training for language models\n• Research engineering or production ML systems\n• Published research or substantial open technical work","status":"open","duplicate_of":null,"first_seen":"2026-11-04T01:52:02.259799+00:00","responsibilities_summary":null,"requirements_summary":null,"all_tools":["LLM"],"posting_language":"en","evidence":[],"years_experience_max":null,"mobility_evidence":[],"model_version":"rules-8","english_badge":"English required","company_id":3641}