engineering Programming Tutorials & Engineering Articles

How we built an agentic system that autonomously builds and maintains integrations as customers ask for them

ClickStack and Hud now share trace IDs, pairing service-level observability with function-level runtime forensics so coding agents can assess risky changes before they ship, catch regressions right after deploy, and fix them with real production context.

How customer needs shaped Oxide's Kubernetes integrations.

HeyGen ported their 18B+ parameter Avatar IV video generation model to Google Cloud's Trillium (v6e) TPUs via torchax and XLA, utilizing FSDP and Ulysses sequence parallelism across an eight-chip mesh. To achieve a 1.86x speedup for real-time streaming, the engineering team pipelined exposed all-to-all collectives, aligned sparse attention block sizes to eliminate mask padding, and bypassed softmax serial dependencies using a precomputed Cauchy-Schwarz upper bound. These custom Pallas kernel and compiler optimizations were deployed only after passing rigorous two-tier quality gates to guarantee byte-identical or mathematically equivalent pixel outputs.

We rebuilt our mobile end-to-end testing framework with a strict API and computer vision, raising test stability drastically.

WhatsApp is committed to helping people stay safe while protecting the privacy of their messages. As scam tactics evolve — from impersonation to social engineering to AI-generated lures — we’…

Video is a core data path across NVIDIA Jetson applications, from robotics and intelligent video analytics to industrial automation, healthcare…

Learn how NVIDIA NeMo Switchyard routes AI agent workloads across models using tuning-free and tunable routers that balance model capability, cost, and latency.

As AI coding assistants shift the developer's primary role from writing boilerplate to reviewing and maintaining systems, language choice becomes critical for long-term architectural integrity. Go directly addresses this new paradigm by utilizing its strict compiler, integrated toolchain, and uncompromising readability to provide deterministic guardrails that help AI models self-correct and generate highly standardized code. By enforcing ecosystem-wide consistency and strict backward compatibility, the Go platform empowers engineering teams to efficiently verify, optimize, and maintain high-velocity, AI-generated output in production environments.

While a smart fridge can detect when a household is running out of milk, the more interesting engineering problem begins after that.

How we compress production failures into model weights every day, beat frontier-model quality, and cut serving costs 96%.

Every day, Meta’s recommendation platforms handle billions of user interactions, generating rich temporal signals that capture individual preferences and intent across products, ads, and content. I…

I am excited to announce that I am joining ClickHouse, Inc. to establish and lead a new research team at ClickHouse Labs.

Meta’s Generative Ads Recommendation Model (GEM), the foundation model behind ads recommendations across Instagram and Facebook, now trains at LLM scale on several thousand of the latest-gene…

We ran ClickHouse Managed Postgres and PlanetScale on the same hardware. ClickHouse delivered up to 54% higher throughput with lower latency.

To prevent context window bloat and reduce token consumption, Genkit Go introduces Agent Skills based on a progressive disclosure architecture. Developers can package specialized instructions, scripts, and references into modular SKILL.md bundles where only the frontmatter metadata is initially exposed to the agent's system prompt. When a task matches the skill's description, Genkit's middleware dynamically loads the full instruction body and associated assets, ensuring the model accesses precise workflows exactly when needed.

NVIDIA nvmath-python is a library designed to bridge the gap between the Python scientific community and NVIDIA CUDA-X math libraries. It gives Python users…

Knowledge workers are increasingly integrating AI agents into their workflows. Agents that function as “digital coworkers” offer clear benefits. For example…

Stripe's Knowledge AI Platform is our versatile AI agent platform built to handle diverse non-coding knowledge work, from quick queries to complex, multi-day projects. By connecting employees to over 1,000 internal tools and skills, it enables secure, enterprise-scale productivity across the organization.

Google's open-source TPU microbenchmark suite provides developers with granular performance metrics across Network, Compute, HBM, Host Transfer, and Attention components to validate real-world hardware capabilities. By leveraging these benchmarks to establish a Roofline model, engineers can accurately diagnose whether their machine learning workloads are compute-, memory-, or network-bound. This empirical baseline directly guides targeted software optimizations—such as kernel tuning, mesh sharding, and rematerialization—to maximize hardware utilization for large-scale model deployments.

Deploying an AI coding assistant in a regulated, sovereign, or source-sensitive environment, often comes with challenges. Three common issues are: the source…

One user turn can contain many model and tool iterations. Any cost inside the repeated region can be paid many times.

By Justin Uberti and Zahan Malkani, Members of Technical Staff

Oxide joins Anthropic's Project Glasswing, applying Claude Mythos 5 to find and patch vulnerabilities across its open-source stack, firmware to network.

Unlike autonomous driving or industrial robotics, healthcare robotics can’t rely on internet-scale data collection or unlimited real-world experimentation.

How Airbnb teams build trustworthy Generative AI products by treating evaluation as a first-class engineering discipline; not an…

Building a great AI agent isn’t just about choosing the right models. The harness is the architecture surrounding the model. How it renders context…

Modern chip design is increasingly limited by engineering time. Register transfer level (RTL) development and verification require specialized hardware…

As AI workloads increase, explosive compute demand is pushing the semiconductor industry to meet unprecedented performance targets. Even small delays can have…