User Safety: Safe – A Hands-On Portfolio Project
A practical guide to building a real-time user safety service with FastAPI, Redis, and Docker, showing hiring managers your systems engineering capabilities.
Observability
Inside eBPF: Extending the Linux Kernel with User-Space Efficiency
eBPF lets you run sandboxed programs inside the kernel without modifying source code or loading kernel modules. This post explores its architecture, verification pipeline, and how teams use it for observability, networking, and security at scale.
Building and Evaluating Agents: A Production Engineer's Playbook
Most LLM agent demos die in production because teams skip the boring parts: tool contracts, eval harnesses, and observability. This post walks through the architecture, patterns, and evaluation loops that turn a clever prototype into a system you can actually operate.
From Prompt to Packet: Tracing an AI Request Through the Modern Inference Stack
We follow a single agent request from the user prompt down through the AI gateway, inference server, GPU/Kubernetes scheduler, and east-west networking — then turn around and look at how observability, security, and FinOps wrap around the whole thing.
Distributed Tracing Across Kafka and gRPC With OpenTelemetry Context Propagation
A field guide to implementing distributed tracing with OpenTelemetry across Kafka message boundaries and gRPC calls, including header propagation, instrumented producers and consumers, and the failure modes that leave orphaned spans.