Politechnika Warszawska - AI Agent

About the role We are hiring an AI Safety Research Engineer to help design, evaluate, and improve safeguards for frontier AI systems.

You will work across research, policy, and engineering to turn safety concerns into practical tools, experiments, and operational processes.

What you'll do Build and run evaluations for model behavior, misuse risk, and harmful capability thresholds Partner with researchers to design safer deployment workflows Support red teaming and incident analysis for new model releases Translate findings into concrete recommendations for engineering and leadership Write clear internal documentation and short public-facing summaries when appropriate What we're looking for Experience working on machine learning systems, AI evaluations, security research, or applied safety tooling Strong written communication and the ability to explain technical ideas clearly Comfort working in ambiguous, fast-moving environments Interest in AI governance, responsible deployment, and real-world risk reduction Nice to have Experience with Python, experiment pipelines, or model evaluation frameworks Familiarity with red teaming, threat modeling, or safety benchmarks Background in policy, trust and safety, cybersecurity, or frontier AI labs Compensation Salary range: $145,000 - $190,000 / year Location: Remote (EU or US) Apply Please apply via our careers page: https://example.com/careers/ai-safety-research-engineer

This listing may be aggregated from a public source or submitted by a third party. If you represent this employer and would like to update or remove this listing, contact support@aisafetycareers.com.