Verified skills

Execute QA test plans on Holoscan Sensor Bridge hardware by reading a test document, filtering tests by setup, running automatable tests with pass/fail evaluation, and producing a structured report.

Evaluates RAG pipelines using a filesystem-based benchmark with corpus/ and train.json, running evaluate_rag.py to tune retrieval and generation flags and interpret RAGAS metrics.

Run config-driven performance benchmarks against a deployed NVIDIA RAG Blueprint server, including profiling and load testing, with a unified report.

Flash FPGA firmware on HSB Lattice boards and Leopard Imaging VB1940 cameras connected to NVIDIA devkits, with safety checks and multi-step upgrade/downgrade procedures.

Set up the Holoscan Sensor Bridge demo environment end-to-end: clone the repo, configure the host per platform, build and run the demo container, and verify connectivity to the sensor board.

Installs, deploys, runs, validates, troubleshoots, and stops NVIDIA AI-Q Blueprint infrastructure for local or self-hosted servers.

Guide users through installing CUDA-Q, writing quantum kernels, running GPU-accelerated simulations, connecting to QPU hardware, and exploring built-in applications.

Runs deep research queries through a reachable NVIDIA AI-Q Blueprint backend, handling health checks, job submission, polling, and report retrieval.

Update docs/index.md and write Google-style docstrings for NeMo-RL documentation changes.

Install cuOpt for Python, C, or REST server via pip, conda, or Docker, and verify the installation.

Build synthetic datasets and data generation pipelines using the Data Designer library.

Guides testing Megatron-LM: test layout, recipe YAML, adding and running unit/functional tests, golden values, marker filters, and CI parity.

Runs chest X-ray reasoning smoke tests using the NV-Reason-CXR-3B model via local inference or a public Hugging Face Space API.

Segments abdominal organs from CT NIfTI volumes using the NV-Segment-CT VISTA3D model, producing label maps and structured evidence JSON.

Deploy, configure, troubleshoot, and manage NVIDIA RAG Blueprint deployments across Docker, Helm, and library setups.

Ask visual questions about video clips using a VSS agent's video_understanding tool, requiring a fresh look at frames rather than prior metadata or search results.

Build video analytics pipelines using NVIDIA DeepStream SDK 9.0 with Python pyservicemaker API, including GStreamer-based video processing, TensorRT inference integration, object detection/tracking, and Kafka/message broker integration.

Inspects the host system, assesses platform compatibility, and recommends the correct Holoscan SDK installation method, then delegates to a method-specific install skill.

Selects Jetson-compatible containers, vLLM runtime images, and Jetson AI Lab PyPI indexes based on Orin SM 8.7 vs Thor SM 11.0 and JetPack version.

Launch, monitor, stop, and debug NeMo-RL recipes on a Kubernetes cluster using the nrl-k8s CLI, supporting ephemeral and long-lived RayCluster modes.

Split a large pull request into multiple smaller PRs to reduce the number of required CODEOWNERS reviewer groups.

Index folders of PDFs and other documents into LanceDB for vector search, then query them with semantic search, page filters, verbatim quotes, and cross-document aggregation.

Generates synthetic body MRI volumes using NVIDIA's NV-Generate-CTMR rflow-mr model. Wraps the upstream diffusion inference pipeline with config staging, output validation, and NIfTI volume summarization.

Run automated hyperparameter optimization for NVIDIA TAO models using AutoMLRunner, supporting multiple search algorithms and experiment tracking.

Train, evaluate, export, distill, quantize, or run inference for a TAO DINO 2D object detector using transformer-based detection with denoising training and multi-scale features.

Trains, evaluates, exports, and runs inference for person re-identification models using TAO, learning discriminative embeddings for cross-camera matching.

Modify, build, test, debug, and contribute to the NVIDIA cuOpt codebase (C++/CUDA, Python, server, CI). Includes guidance for solver internals, pull requests, DCO signoff, and code conventions.

Routes NVIDIA Nemotron Speech (Riva) NIM tasks for ASR, TTS, and NMT, covering cloud-hosted inference, self-hosted Docker deployment, and custom model builds.

Runs NV-Segment-CTMR segmentation on CT or MRI NIfTI volumes and records label-map evidence.

Manage NVIDIA Brev GPU instances for TAO training, evaluation, and inference using the Brev CLI and Docker.

Guides users through installing, configuring, and calling the NVIDIA cuOpt SDK for routing and optimization problems, with emphasis on clarifying requirements and safe execution.

Read and write large cuPyNumeric arrays to HDF5 files using Legate's parallel, distributed HDF5 I/O.

Bind pre-downloaded Jetson reference docs (developer guide, design guide, pinmux, schematics) into the active profile documents block. Use after staging docs on disk; not for downloading.

Serve LLMs and VLMs on NVIDIA Jetson devices using vLLM or SGLang with optimized Docker containers and quantization presets.

Automates the full DEFT AOI improvement loop for NVIDIA TAO VisualChangeNet / ChangeNet PCB inspection models, including baseline evaluation, RCA, synthetic defect generation, data mining, retraining, and deployment gating until KPI targets are met.

Submit and manage TAO training, evaluation, and inference jobs on SLURM GPU clusters over SSH with sbatch/srun, Pyxis/Enroot containers, and Lustre-backed storage.