Projects
This could be a subhead about the projects on this page.
From context to dreams: architecting memory for AI agents
Benchmarking AI inference on CPUs: A transparent blueprint for the enterprise
Zero trust for AI agents: why delegation beats impersonation
Who’s really calling? Securing agent-to-agent communication
Code execution with MCP: How sandboxed Python replaces tool schema bloat in AI agents
PyTorch Call Stack Deep Dive: Tracing Tensor Operations from Python to C++ Kernels
Eliminating the ‘Rego tax’: How AI orchestrators automate Kubernetes compliance
Zero trust AI agents on Kubernetes: What I learned deploying multi-agent systems on Kagenti
Zero Trust for autonomous agentic AI systems: Building more secure foundations
From hand-tuned to generated: A reproducible Triton GPU kernel benchmark across different vendors
Protecting Triton kernel deployments with cryptographic signatures
Skip the JITters: Fast, trusted model kernels with OCI caching
No results found.