aws·May 27, 2026·2 min readCurated summary

Meet Our Newest AWS Heroes – May 2026 | Amazon Web Services

AWS has named four new Heroes for May 2026, recognizing leaders who advance cloud, AI, serverless, and community education. Their work ranges from building Amazon Bedrock-powered tools and contributing to AWS certifications to organizing major user groups and events across Europe and Latin America. Together, they demonstrate how technical expertise and community leadership can help more builders adopt AWS. ## Damiano Giorgi — Pavia, Italy - An Artificial Intelligence Hero and Cloud Solutions Architect specializing in AI. - Helps organize AWS User Groups in Pavia and Milan. - Created the “Unofficial post:Invent Session Suggester,” using Amazon Bedrock and Amazon Nova to recommend re:Invent sessions. - Shares knowledge through his “Bass and Bytes” blog and conferences across Europe. ## Darryl Ruggles — Ottawa, Canada - A Serverless Hero and Cloud Solutions Architect with a background in software development. - Focuses on AWS application architecture, AI/ML, serverless, containers, and FinOps. - Publishes blog posts, LinkedIn content, and open projects. - Participates actively in online communities such as “Believe In Serverless” and in-person AWS events. ## Ricardo Daniel Ceci — Buenos Aires, Argentina - An Artificial Intelligence Hero leading the AWS User Group Buenos Aires, with nearly 2,400 members. - Principal organizer of AWS Community Day Argentina. - Named AWS Community Leader of the Year 2025 for Latin America. - Hosts a podcast with cloud experts, AWS Heroes, and developer advocates. - Works to make cloud and AI more accessible to Spanish-speaking builders across LATAM. ## Matias Kreder — Buenos Aires, Argentina - An Artificial Intelligence Hero and AWS Certification Subject Matter Expert. - Contributed to AI/ML certifications, including the AWS Certified AI Practitioner exam. - Began his community involvement through AWS DeepRacer, qualifying as a finalist three times. - Organizes racing events, ML talks, and AWS community activities across Latin America. - Helped organize AWS Community Day Argentina 2025 and speaks at regional events. These new Heroes illustrate the value of combining AWS expertise with mentorship, content creation, certification work, and community organizing. Builders can learn more or connect with regional leaders through the AWS Heroes program.

Read original(opens in new tab)

Amazon NovaAIMachine LearningAWS+4

aws·Feb 16, 2026·3 min readCurated summary

Announcing Amazon SageMaker Inference for custom Amazon Nova models | Amazon Web Services

Amazon SageMaker Inference now generally supports deploying and scaling full-rank customized Amazon Nova models. The feature gives production workloads more control over instance types, autoscaling, context length, concurrency, and batch settings while improving cost efficiency through optimized GPU utilization. Customers can train Nova Micro, Nova Lite, and Nova 2 Lite models with SageMaker Training Jobs or HyperPod, then deploy them as managed real-time or asynchronous endpoints. ## Custom Nova Model Support - Supports customized Nova Micro, Nova Lite, and Nova 2 Lite models. - Models can use: - Continued pre-training - Supervised fine-tuning - Reinforcement fine-tuning - Custom models can be trained through Amazon SageMaker Training Jobs or Amazon HyperPod. - SageMaker Inference provides managed deployment, scaling, and HTTPS access for production workloads. - GPU utilization and inference costs can be optimized with Amazon EC2 G5 and G6 instances instead of relying exclusively on P5 instances. - Autoscaling can respond to five-minute usage patterns. - Configurable context length, concurrency, and batch size help balance latency, cost, and accuracy. ## Deploying Through SageMaker Studio - In SageMaker Studio, users select a trained Nova model from the Models menu. - Choosing **Deploy**, **SageMaker AI**, and **Create new endpoint** starts deployment. - Deployment settings include: - Endpoint name - Instance type - Initial and maximum instance counts - Permissions - Networking configuration - Supported launch instance types vary by model: - Nova Micro: G5, G6, and P5 options, including `g5.12xlarge` through `g6.48xlarge` and `p5.48xlarge` - Nova Lite: `g5.48xlarge`, `g6.48xlarge`, and `p5.48xlarge` - Nova 2 Lite: `p5.48xlarge` - Provisioning takes time because SageMaker must create infrastructure, download model artifacts, and initialize the inference container. - Once the endpoint is `InService`, users can test it in the Studio Playground using chat prompts. ## Deploying with the SageMaker SDK - Deployment requires two SageMaker resources: - A model object referencing the Nova artifacts and inference container - An endpoint configuration specifying the instance type and count - Model artifacts can be stored in Amazon S3 and referenced with an S3 prefix. - Environment variables configure inference behavior, including: - `CONTEXT_LENGTH` - `MAX_CONCURRENCY` - `DEFAULT_TEMPERATURE` - `DEFAULT_TOP_P` - The endpoint configuration creates a real-time endpoint, such as one using an `ml.g5.12xlarge` instance. - SageMaker supports network isolation and execution roles for secure deployment. ## Inference and Request Configuration - Endpoints support synchronous real-time inference in streaming or non-streaming modes. - Asynchronous endpoints are available for batch-style processing. - Requests can configure: - Maximum output tokens - Temperature - Top-p and top-k sampling - Log probabilities - Streaming usage statistics - Reasoning effort, with `low` and `high` options - The example request asks the model to compare quarterly spending against budget and identify variances above 10 percent. SageMaker Inference provides a complete path from Nova customization to production deployment. Teams should select instance types and tune context length, concurrency, batching, and sampling parameters based on their workload’s latency, cost, and accuracy requirements.

Read original(opens in new tab)

Amazon NovaMachine LearningAWSAmazon Ec2+3