Build Production-Ready Drug Discovery and Robotics Pipelines with NVIDIA NIMs on SageMaker JumpStart
Amazon SageMaker JumpStart now enables one-click deployment of four NVIDIA NIMs models purpose-built for biosciences and physical AI: ProteinMPNN, Nemotron-3.5B-Instruct, MSA Search NIM, and Cosmos Reason. NVIDIA NIM™ provides prebuilt, optimized inference microservices for rapidly deploying the latest AI models on any NVIDIA-accelerated infrastructure. These models bring advanced capabilities spanning protein design, reasoning with configurable outputs, and physical world understanding, enabling customers to accelerate biosciences research, drug discovery, and embodied AI applications on AWS infrastructure.
ProteinMPNN enables fast and efficient protein sequence optimization guided by structural data. This NIM generates high-quality sequences with enhanced binding affinity and stability, validated through experimental results. Designed for scalability and flexibility, ProteinMPNN integrates seamlessly into protein engineering workflows, transforming applications like enzyme design and therapeutic development.
MSA Search NIM supports GPU-accelerated Multiple Sequence Alignment (MSA) of a query amino acid sequence against a set of protein sequence databases. These databases are searched for similar sequences to the query and then the collection of sequences are aligned to establish similar regions even when the proteins have different lengths and motifs.
Nemotron-3.5B-Instruct delivers high reasoning performance, native tool calling support, and extended context processing with 256k token context window. This model employs an efficient hybrid Mixture-of-Experts (MoE) architecture to ensure higher throughput than its predecessors for agentic and coding workloads, while maintaining the reasoning depth of a larger model. It is ideal for building multi-agent workflows, developer productivity tools, processes automation, and for scientific and mathematical reasoning analysis, amongst others.
Cosmos Reason is an open , customizable, reasoning vision language model (VLM) for physical AI and robotics. It enables robots and vision AI agents to reason like humans, using prior knowledge, physics understanding, and common sense to understand and act in the real world. This model understands space, time, and fundamental physics, and can serve as a planning model to reason what steps an embodied agent might take next.
With SageMaker JumpStart, customers can deploy any of these models with just a few clicks to address their specific AI use cases.
To get started with these models, navigate to the SageMaker JumpStart model catalog in the SageMaker console or use the SageMaker Python SDK to deploy the models to your AWS account. For more information about deploying and using foundation models in SageMaker JumpStart, see the Amazon SageMaker JumpStart documentation.