-
Beating Claude Opus 4.5 at Kernel Generation with a 3B-Active RL Agent
A 30B MoE model with only 26.7M LoRA parameters generates faster NKI kernels than Claude Opus 4.5 — achieving 1.47x speedup and 94% fast rate on 250 benchmark tasks.
-
AWS Guidance for AI-Driven Robotic Simulation and Training on AWS
Build an AI-powered robot training and fleet management system using Amazon Bedrock foundation models and AWS IoT. Combines imitation learning with NVIDIA Isaac on Amazon EC2 and reinforcement learning with edge-optimized reward functions to train robots for precise tasks and manage fleets at scale.
-
How BMW Group and Qualcomm built an automated driving platform on AWS
End-to-end automated driving platform combining Qualcomm's in-vehicle compute with AWS cloud services. Enables scalable data processing, large-scale simulation, and continuous L2+ feature development — from data collection in the vehicle to model training and validation in the cloud.
-
Scaling LLM Inference on EKS with AWS Inferentia and Trainium
Deploy and scale large language model inference workloads on Amazon EKS using AWS Inferentia and Trainium accelerators. Covers model compilation with Neuron SDK, container packaging, and Kubernetes-native autoscaling to achieve cost-efficient, low-latency serving at production scale.
-
Secure and Flexible Access Control for Regulated Workloads: A Guide to Implementing Role-Based Access
Implement fine-grained role-based access control for regulated industries running workloads on AWS. Walks through IAM policy design, permission boundaries, and service control policies that balance security compliance with developer agility across multi-account environments.