AI Safety Research Engineer — Evaluation & Tools
Listed on 2026-07-16
-
IT/Tech
AI Evaluation, Cybersecurity, AI Engineer (Applied/Software)
AI Safety Researcher
Research
Full-time
Actively Hiring
Conduct cutting-edge research on AI safety, focusing on adversarial robustness, interpretability, and alignment. Publish findings and contribute to safety tools.
Requirements- • PhD or equivalent experience in AI/ML, computer science, or related field
- • Strong publication record in AI safety, robustness, or related areas
- • Experience with red teaming or adversarial testing of AI systems
- • Proficiency in Python and ML frameworks (PyTorch, Tensor Flow)
Full-time
Actively Hiring
Build and maintain secure infrastructure for AI model evaluation and deployment. Design security controls, implement monitoring systems, and respond to incidents.
Requirements- • 5+ years of experience in security engineering or related field
- • Deep understanding of application security, cloud security, and cryptography
- • Experience with infrastructure-as-code (Terraform, Cloud Formation)
- • Familiarity with AI/ML systems and their unique security challenges
Operations
Remote
Full-time
Actively Hiring
Lead adversarial testing campaigns against frontier AI models. Develop novel jailbreak techniques, identify security vulnerabilities, and assess misuse potential.
Requirements- • Extensive experience in offensive security, penetration testing, or red teaming
- • Deep understanding of LLM capabilities and limitations
- • Creative problem-solving and adversarial thinking
- • Strong communication skills for reporting findings
Full-time
Actively Hiring
Build evaluation frameworks, benchmarks, and tools for AI safety research. Collaborate with researchers to translate ideas into production-ready systems.
Requirements- • Strong software engineering skills with Python
- • Experience building ML infrastructure or research tooling
- • Familiarity with AI safety concepts and evaluation methodologies
- • Ability to work at the intersection of research and engineering
Policy
Washington DC / Remote
Full-time
Actively Hiring
Shape AI safety policy, contribute to standards development, and engage with government agencies. Translate technical research into actionable policy recommendations.
Requirements- • Experience in AI policy, technology policy, or related field
- • Strong understanding of AI capabilities and safety challenges
- • Excellent writing and communication skills
• Existing relationships with policymakers or standards bodies preferred
(If this job is in fact in your jurisdiction, then you may be using a Proxy or VPN to access this site, and to progress further, you should change your connectivity to another mobile device or PC).