Inspect LLM torch profiler traces at forward-pass, layer, and kernel level.
Investigate LLM output quality issues — trace hallucination root causes across context, retrieval, prompts, tool use, and workflow design
Parse SGLang/vLLM startup logs to explain GPU memory use and request capacity.
Security patterns for autonomous trading agents with wallet or transaction authority.
Manages lightweight, folder-based Markdown knowledge bases with fast offline vector search, BM25 indexing, and automated AI note ingestion.
LLMs and Generative AI: 83 concepts, no maths assumed.
Generates Docker and docker-compose configuration for multi-container development
Configures CORS policy for development and production environments.
Load files, object storage, dataframes, or external databases into MotherDuck using an appropriate bulk ingestion path.
Write a load and performance testing plan for a service.
Run plan → still → video → audit fully local.
Guides users through the process of preparing datasets and fine-tuning local Large Language Models (LLMs) using techniques like LoRA and…
Run OCR on local images through an OpenAI-compatible local vision endpoint (LM Studio, vLLM/vmlx).
Set up and manage local skills for automatic matching and invocation
Use when implementing localization (i18n/l10n) — TranslationServer, CSV/PO translation files, locale switching, RTL support, and…
Use when localizing apps, using String Catalogs, generating type-safe symbols (Xcode 26+), handling plurals, RTL layouts, locale-aware…
Designs location-based augmented reality experiences with geospatial anchoring, GPS integration, and real-world interactive overlays.
Automate Lodgify tasks via Rube MCP (Composio).
Logs unanswered questions to the Knowledge Gaps list and routes them to a subject matter expert.
Run Python code in the cloud with serverless containers, GPUs, and autoscaling.
Turn the raw inventory of P1 into a logical map of the codebase: modules, packages, namespaces, layers and the architectural pattern (or…