AI’s Next Revolution: Multiply Labs Is Scaling Robotics-Driven Cell Therapy Biomanufacturing Labs
Source: NVIDIA AI Blog
Overview
Multiply Labs is doing for cell‑therapy labs what has already happened in the chip industry: it introduces robots to perform tedious, precision‑driven, hygienic work faster, better, and cheaper.
The concept was sparked when Fred Parietti was doing PhD research in robotics at MIT and met Alice Melocchi, who showed him how labor‑intensive labs lacked automation while risking contamination.
“She showed me what she did in a lab and how difficult it was, and I couldn’t believe it — I thought drugs were made like chips, and this was insane but also real,” said Parietti, co‑founder and CEO of Multiply Labs. “Next, I flew to Silicon Valley, and we started this at Y Combinator.”
San Francisco‑based Multiply Labs, founded in 2016, now automates cell‑therapy manufacturing for leading companies such as Kyverna Therapeutics and Legend Biotech.
What Multiply Labs Offers
- End‑to‑end robotic systems for producing gene‑modified cell therapies at scale – see the full product line here.
- Digital twins of lab environments built with NVIDIA Omniverse.
- Robotics simulation & training using the NVIDIA Isaac Sim framework.
- Development of humanoid robots based on the NVIDIA Isaac GR00T foundation model to assist in labs with enhanced hygiene.
These technologies bring precision gains, reduced contamination, and advanced manufacturing powered by physical AI (NVIDIA definition).
Why Automation Matters for Cell Therapies
Cell therapies involve extracting cells from a patient or donor, genetically modifying them, and re‑infusing them to treat cancers, genetic disorders, autoimmune diseases, and neurological conditions.
- Artisanal nature – each treatment is often a one‑off for a specific patient.
- High cost – manufacturing is expensive and highly sensitive to contamination or mishandling.
- Sterility requirement – any breach (e.g., breathing near the cells) can ruin the product.
“It needs to be sterile, and you don’t want anyone breathing anywhere near the cells, so it was an obvious high‑value application of robotics,” says Parietti.
Robots operating within Multiply Labs’ controlled biomanufacturing clusters provide hygienic, precise, and repeatable processes, dramatically lowering risk and cost.
References
- Multiply Labs website
- Cell‑therapy product page
- NVIDIA Omniverse
- NVIDIA Digital Twin glossary
- NVIDIA Isaac Sim
- NVIDIA Isaac GR00T
- Physical AI definition
Simulating Cell Therapy Manufacturing Skills for Improved Precision in Labs
Cell therapy manufacturing is complex, costly, and prone to failure. Bioscience companies are turning to automation and simulation to reduce risk, scale output, and preserve expert knowledge. A key development is imitation learning—training robots in Isaac Sim to replicate expert tasks by analyzing video demonstrations. This approach captures the tacit, often undocumented skills of top scientists and translates them into robotic control policies.
“We’re literally training the robot on the exact video example of the best scientist, and we prove that they are statistically equivalent,” said Parietti.
“If people leave or retire, yield can go down — we observe that there can be a lot of implicit knowledge in these operations, it’s almost like an art.”
Core Technologies
- NVIDIA FoundationPose – an Isaac model for pose estimation.
- NVIDIA FoundationStereo – an Isaac model for stereo matching.
These models extract trajectories from video, enabling robots to learn directly from the best human examples. This is especially vital in pharma, where tech‑transfer of processes from labs to production environments is critical, and where knowledge loss due to staff turnover can cripple production.
Digital‑Twin Simulation
Multiply Labs uses digital twins built in NVIDIA Omniverse to simulate robot‑arm processes. By running thousands of virtual iterations, the company can:
- Identify and resolve mechanical bugs before physical deployment.
- Accelerate development cycles.
- Increase safety and precision in laboratory operations.
Scaling Up Robotic Systems to Make Cell Therapies More Accessible
Cell and gene therapies hold extraordinary promise, but their complexity and cost have historically limited access. Automation is changing that.
Today, manufacturing a single dose of cell therapy can cost upwards of $100,000. Through advanced robotics, that cost can be reduced by more than 70 %, bringing it down to $25,000 – $35,000 per dose.
“We want to enable the shift of the industry from niche to scale — 100 times more therapies at 70 % less cost — so life‑saving treatments aren’t just for the few, but for the millions.” – Parietti
Why Automation Matters
- Cost reduction: Up to 70 % lower manufacturing expenses.
- Throughput boost: Up to 100 times more therapies per square foot of facility space.
- Precision & consistency: Robots perform thousands of sterile steps—liquid transfers, bag/syringe stirring, temperature control—without introducing bubbles or human error.
- Continuous operation: Robots don’t need breaks and maintain traceability 24/7.
The Process
These therapies involve thousands of precise, sterile steps—moving liquids between vessels, stirring bags and syringes without introducing bubbles, maintaining exact temperatures—all within tight time constraints. Human error, even in a single step, can compromise the entire process. Robots, on the other hand, execute each task with precision, consistency, and traceability around the clock.
Video Overview
Your browser does not support the video tag.
Your browser does not support the video tag.(Replace path-to-video.mp4 with the actual video file URL.)
Harnessing Humanoids to Improve Processes for Contamination
In the high‑stakes world of cell‑therapy manufacturing, contamination isn’t just a nuisance—it’s a show‑stopper. Robotic arms inside the controlled cluster environment operate with surgical precision, but the real “wild‑west” lies just outside that clean room. Loading and unloading materials manually introduces the risk of a sneeze, a slip, or a dropped syringe—any of which can compromise a pristine process.
Why Humanoids?
- Adaptable – Two‑armed workhorses that can handle unstructured, unpredictable environments.
- Precise – Capable of picking up cartridges, moving them carefully, and maintaining sterility.
- Scalable – Once trained, the same skills can be deployed across many workstations.
NVIDIA Isaac GR00T N Foundation Model
Multiply Labs is developing humanoids with NVIDIA’s Isaac GR00T N foundation models.
- GR00T N1.5 is an open‑robot foundational model for generalized humanoid reasoning and skill acquisition.
“GR00T gives our humanoids the muscle memory of a thousand lifetimes,” says Parietti. “It’s like teaching a robot to dance by showing it a few steps.”
With Isaac GR00T, training humanoids to handle loading and unloading becomes a scalable, repeatable process:
- Capture messy human demonstrations.
- Convert them into clean control policies.
- Deploy the policies rapidly across multiple robots.
The Result
A fully automated manufacturing floor where humans observe from behind glass, while humanoids—powered by Isaac GR00T—keep the process flowing, clean, and contamination‑free.
Image credit: NVIDIA Blog