Director, Autonomous Lab AI & Discovery

Johnson & Johnson Co.; Spring House (PA); On-site; USD 164,000 - 283,000; Full time

Job summary

Johnson & Johnson is recruiting for a Director, Physical AI for Autonomous Discovery to join the In Silico Drug Discovery team. The preferred location is Spring House, PA, with travel as needed; Cambridge, MA nearby options may be considered. No remote option.

The role leads the Physical AI strategy, combining AI, robotics, and scientific reasoning to enable autonomous laboratory experimentation and self‑improving discovery workflows, partnering across IT, data science, and discovery scientists.

Qualifications

• PhD in artificial intelligence, machine learning, robotics, computer science, engineering, computational biology, or a related quantitative field.
• Demonstrated experience developing AI systems that operate in physical or scientific environments.
• Deep expertise in world models, reinforcement learning, Bayesian optimization, causal inference, multimodal AI, robotics, or scientific machine learning.
• Strong software-development skills, including Python and modern machine-learning frameworks.
• Ability to translate scientific and operational requirements into robust, scalable AI models and to communicate across multidisciplinary teams.
• Strong collaboration skills to work in matrix environment.

Responsibilities

• Define and execute the Physical AI strategy, build and lead a high-performing team, and establish a roadmap aligned with scientific priorities and business objectives.
• Develop AI models that understand and reason about instruments, samples, reagents, robotic systems, workflows, and laboratory state.
• Build adaptive experimental optimization capabilities using active learning, Bayesian optimization, reinforcement learning, and multi-objective optimization.
• Create systems for physical error detection and correction, including anomaly recognition, root-cause assessment, workflow replanning, recovery actions, and appropriate human escalation.
• Develop models that generate hypotheses for experimental failures, unexpected results, variability, and irreproducibility, and recommend discriminating follow-up experiments.
• Design agentic and multi‑agent systems that coordinate experiment planning, execution monitoring, data interpretation, and decision‑making across Design‑Make‑Test‑Analyze cycles.
• Partner with automation, robotics, data science, engineering, and discovery scientists to deploy reliable closed-loop learning in real laboratory environments.
• Embed calibrated uncertainty, safety constraints, monitoring, traceability, and governance into autonomous decision‑making.

Skills

PhD in AI/ML or related field

World models

Reinforcement learning

Bayesian optimization

Causal inference

Multimodal AI

Robotics / lab automation

Python & ML frameworks

Education

PhD inAI/ML or related field

Tools

Python

ML frameworks

Robotics software

MLOps

Job description

Johnson & Johnson is recruiting for a Director, Physical AI for Autonomous Discovery to join the In Silico Drug Discovery team. The preferred location is Spring House, PA, with travel as needed; Cambridge, MA nearby options may be considered. No remote option.

The role leads the Physical AI strategy, combining AI, robotics, and scientific reasoning to enable autonomous laboratory experimentation and self‑improving discovery workflows, partnering across IT, data science, and discovery scientists.