Physical AI Engineer - Lilly Medicine Foundry

About the Role

As a Physical AI Engineer, in partnership with other teams you will deploy advanced AI models into robotic, computer vision and sensor-based systems that make the Lilly Medicine Foundry safer, faster and more resilient. You will build and integrate edge-to-cloud patterns that connect cameras, sensors, AGVs, co-bots, drones and quadrupeds to the Foundry data platform, manufacturing execution and closed-loop quality systems, and you will use simulation and digital twins to validate those systems before they reach GMP areas.

Key Responsibilities

• Lead the deployment and integration of advanced AI models (machine learning, computer vision, generative AI and agents, reinforcement learning) into robotic and sensing systems including cameras, AGVs, co-bots, drones and quadruped robots.
• Design, build and operate the edge-to-cloud reference architecture from sensor to decision, including GPU edge inference, cloud model training on AWS, OT/IT data ingestion, and orchestration with an ontology spanning all layers.
• Optimize AI algorithms and models for real-time performance on edge hardware, and manage the model lifecycle including training, versioning, monitoring, drift detection and retraining.
• Build and maintain sim-ready asset libraries and use simulation platforms (e.g., NVIDIA Omniverse, Isaac Sim) to develop digital twins, generate synthetic data, and test robot, co-bot and AGV behavior and safety rules before deployment.
• Integrate vision and sensor outputs with manufacturing execution and quality systems, creating exception queues with audit trails of Quality judgment on every AI flag.
• Develop and implement novel verification methods, testing protocols and performance benchmarks for AI-driven robotics and vision systems in line with GxP and Computer System Validation requirements.
• Work with safety experts to develop and implement safety mitigations, apply and verify safety rules for AGVs and co-bots, and support HSE use cases such as lockout/tagout and near-miss analysis.
• Ensure solutions pass cybersecurity architecture review, apply enterprise data governance and classification to image, video and sensor data, and complete AI intake and risk assessment before deployment.
• Oversee deployment of robotics and vision systems into production operations and provide troubleshooting, technical support and optimization during integration.
• Collaborate with technology and integration partners (e.g., NVIDIA, AWS, robotics, camera and drone vendors) and bridge Digital, Robotics, Facilities and Technology teams.
• Maintain thorough documentation for system deployment, safety protocols, validation and testing results, and AI integration methods, and provide regular reports to stakeholders.

Basic Qualifications

• Bachelor's degree in Robotics, Computer Science, Electrical Engineering, Mechatronics, or a related technical field.
• Minimum of 5 years of experience in robotics, automation, or AI-driven systems deployment in a manufacturing or industrial setting.

Additional Preferences

• Experience deploying computer vision or other AI models at the edge with models trained in the cloud, ideally in a regulated or GMP manufacturing environment.
• Experience with novel safety verification methods and risk analysis for autonomous or semi-autonomous systems, including AGVs and mobile robots.
• Strong programming skills in Python, C++, or ROS.
• Knowledge of AI frameworks (TensorFlow, PyTorch, OpenCV) and model optimization and serving tools (ONNX, TensorRT, Triton).
• Knowledge of industrial communication protocols (OPC-UA, MQTT, Modbus, Ethernet/IP).
• Experience with industrial controls systems and Safety Controllers.
• Experience with edge AI and GPU platforms (NVIDIA Jetson, DeepStream) and edge-to-cloud architectures for vision and sensor data.
• Experience with cloud services for IoT, data and machine learning (AWS IoT Greengrass, SageMaker, S3, GPU compute); familiarity with enterprise data platforms (Databricks, Microsoft Fabric).
• Familiarity with OT/IT data integration and historian platforms (Ignition, Aveva PI, HighByte) and manufacturing execution systems.
• Familiarity with simulation and digital twin tools (NVIDIA Omniverse, Isaac Sim, OpenUSD, CAD) and synthetic data generation.
• Familiarity with generative AI, LLMs and agent frameworks (including MCP) applied to operations, quality or safety use cases.
• Strong analytical skills and a problem-solving mindset with the ability to troubleshoot and optimize hardware and software components of robotic systems.
• Familiarity with industry safety standards and risk mitigation strategies in robotics and automation (ISO 10218, ISO 13482, ISO 3691-4, ISO 13849, EN 61508) and OT cybersecurity practices (IEC 62443).
• Excellent communication and teamwork abilities with a customer-centric approach and ability to collaborate with external partners and bridge IT, OT, Quality, HSE and facilities teams.
• Solid knowledge of Computer System Validation process and GxP requirements (GAMP 5, 21 CFR Part 11, EU Annex 11), including validation of AI-enabled systems.
• Experience in pharmaceutical or biologics manufacturing operations and with integrating to quality and validation systems.
• Demonstrated ability to analyze, anticipate, and resolve complex issues and effectively prioritize and escalate issues.
• Familiarity with data governance and AI risk-management practices for image, video and sensor data.
• Demonstrated learning agility and curiosity.