AI’s Next Revolution: Multiply Labs Is Scaling Robotics-Driven Cell Therapy Biomanufacturing Labs

2026-01-12 · Source: NVIDIA Blog · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Robotics & Autonomous Systems, Emerging Technologies & Innovation · Depth: Intermediate, medium

Summary

Multiply Labs is revolutionizing cell therapy biomanufacturing by integrating robotics into clean room environments, aiming to reduce costs by over 70% and accelerate output compared to traditional manual systems. Founded in 2016, the San Francisco-based startup automates gene-modified cell therapy production for companies like Kyverna Therapeutics and Legend Biotech. Their systems utilize NVIDIA Omniverse for developing digital twins of lab environments and NVIDIA Isaac Sim for training robots in specific tasks, including imitation learning from expert video demonstrations. Multiply Labs is also developing humanoid robots, powered by the NVIDIA Isaac GR00T foundation model, to assist with material handling outside the controlled clusters, further enhancing hygiene and precision. This approach addresses the high cost and contamination risks associated with artisanal cell therapy production, making these life-saving treatments more accessible.

Key takeaway

For entrepreneurs and investors evaluating opportunities in biotech manufacturing, Multiply Labs' approach demonstrates how advanced robotics and AI can drastically reduce cell therapy production costs from over $100,000 to $25,000-$35,000 per dose, while increasing throughput by 100x. You should consider how similar automation strategies could scale other complex, high-value biomanufacturing processes, making previously niche treatments widely accessible and creating significant market opportunities.

Key insights

Robotics and AI are transforming cell therapy manufacturing, significantly cutting costs and boosting production scale.

Principles

• Automation reduces contamination risk.
• Digital twins accelerate robot deployment.
• Imitation learning captures expert knowledge.

Method

Robots are trained using imitation learning from expert video demonstrations within NVIDIA Isaac Sim, leveraging digital twins from Omniverse to debug processes before physical deployment.

In practice

• Use NVIDIA Omniverse for digital twin simulation.
• Train robots with Isaac Sim and imitation learning.
• Deploy humanoids for external lab logistics.

Topics

• Cell Therapy Biomanufacturing
• Robotics Automation
• NVIDIA Isaac Sim
• Digital Twins
• Imitation Learning

Best for: Investor, Entrepreneur, Robotics Engineer, AI Engineer, AI Product Manager

Related on AIssential

• Robots run this laboratory in Japan — and are changing how scientists work — AI-powered laboratory robots can autonomously manage complex biological experiments, accelerating discovery and freeing human researchers.
• Syntax Bio Announces Expanded Series A and Leadership Appointments — CRISPR-based cellular programming accelerates stem cell differentiation for scalable regenerative medicine.
• Sereact taps Headline to lead $110m Series B, plots US expansion — Real-world data flywheels are crucial for developing robust, adaptable robotics AI beyond lab environments.
• GPT-5 lowers the cost of cell-free protein synthesis — GPT-5 connected to a robotic lab significantly reduced cell-free protein synthesis costs through autonomous closed-loop optimization.
• Rivian spin-out Mind Robotics raises $500M for industrial AI-powered robots — Mind Robotics secured $500M to develop AI-powered industrial robots with human-like dexterity for factory automation.
• ChemT Biotechnology Raises US$5 Million in 18 months to bring AI to Biomanufacturing — AI-driven virtual cell platforms can precisely guide cell behavior to enhance biomanufacturing efficiency and scalability.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by NVIDIA Blog.