
Post Doc - AI Safety
AI
Johnson & Johnson Innovative Medicine is recruiting a Postdoctoral Researcher in AI Safety to join its Data, Data Science & AI organization on a two-year fixed-term appointment. The role involves leading a focused, publishable research program on provable controls, adversarial assurance, and safety-native architecture for agentic AI in regulated pharmaceutical R&D. Candidates need a PhD in computer science, AI/ML, applied mathematics or a related field, first-author research in AI safety/alignment, and hands-on experience with foundation models and agentic AI.
What you'll do
- Execute an independent research agenda on controls, adversarial assurance, or safety-native architecture for agentic AI in regulated scientific settings
- Design rigorous, reproducible experiments—including baselines, ablations, and uncertainty estimates—that test whether a safety property genuinely holds
- Evaluate pre-training data interventions and post-training methods—including supervised fine-tuning, preference optimization, and safety tuning—for regulated scientific use cases
What you need
Must-have
PythonMachine Learning frameworksFoundation modelsAgentic AIRetrieval-augmented generationTool usePlanningMulti-agent frameworks
Nice-to-have
OPA/RegoCedarFormal verification toolsPolicy enginesAuthorization languagesPrivacy-preserving MLData de-identificationData provenance
Soft skills
Written and verbal communicationScientific rigorAbility to present technically defensible arguments
Post DocAI SafetyPharmaceutical ManufacturingAgentic AIAI AlignmentResearchJohnson & Johnson