Sayali Kandarkar
Community@sayalinvidia · NVIDIA HQ, Santa Clara, California, USA
Agent Skills by Sayali Kandarkar
Showing 136 vetted skills indexed across 1 GitHub repositories.
sayalinvidiadynamo-interconnect-check
Assess NIXL/UCX/NCCL transport readiness for Dynamo disaggregated serving.
sayalinvidiadynamo-router-starter
Configure and verify Dynamo frontend router modes across local and Kubernetes deployments.
sayalinvidiaomniverse-usd-performance-tuning
Orchestrate end-to-end USD performance diagnosis and optimization for complex scenes.
sayalinvidiaphysical-ai-infrastructure-setup-and-resilient-scaling
Automate NVIDIA Physical AI infrastructure provisioning and scaling across MicroK8s and Azure AKS.
sayalinvidiaomniverse-realtime-viewer
Route Omniverse Realtime Viewer prompts to focused references and enforce ovrtx-based rendering.
sayalinvidiacuopt-user-rules
Clarify NVIDIA cuOpt usage by asking questions before generating configurations.
sayalinvidiaomniverse-cad-to-simready
Coordinate CAD-to-SimReady workflows for conversion, validation, and packaging.
sayalinvidiaaiq-deploy
Provision and configure local AI-Q deployment backends with validation.
sayalinvidianemo-mbridge-perf-moe-long-context
Guide long-context MoE training with CP heuristics and selective recompute for Megatron Bridge.
sayalinvidiadicom-series-to-volume
Convert a single-series DICOM directory into a HU-scaled NIfTI volume with affine and JSON summary.
sayalinvidianemo-mbridge-perf-parallelism-strategies
Select and tune Megatron Bridge parallelism configurations for model and hardware.
sayalinvidiaskill-card-generator
Assemble governance card context from skill directory signals and render a draft.
sayalinvidianv-generate-mr
Generates synthetic MR images via NV-Generate-CTMR workflow with JSON provenance reporting.
sayalinvidiacudaq-guide
Provides onboarding for CUDA-Q covering installation, kernels, simulation, GPU and QPU access, and applications for Python and C++ workflows.
sayalinvidianemoclaw-user-agent-skills
Catalog NemoClaw agent skills for installation, policy, and operations guidance.
sayalinvidianemotron-customize
Plan and execute Nemotron customization pipelines with per-step YAML configs.
sayalinvidianemotron-policy-generator
Generate BYO safety policies for NVIDIA Nemotron guardrails with Markdown, JSON, and system prompt artifacts.
sayalinvidiadigital-health-clinical-asr-build
Curates clinical terms, annotates IPA pronunciations, and generates NeMo manifests with evaluation audio.
sayalinvidiacuopt-numerical-optimization-formulation
Converts natural-language optimization problems into structured LP/MILP/QP formulations.
sayalinvidiavss-deploy-profile
Deploy and validate NVIDIA VSS profiles with preflight checks and readiness gates.
sayalinvidiamcore-run-on-slurm
Orchestrate distributed Megatron-LM training on SLURM clusters with sbatch skeletons.
sayalinvidiadeepstream-dev
Automate NVIDIA DeepStream pipeline construction using the pyservicemaker API.
sayalinvidianemo-mbridge-perf-tp-dp-comm-overlap
Configure TP, DP, and PP communication overlap in Megatron-Bridge training.
sayalinvidiaholoscan-install-conda
Installs Holoscan SDK and dependencies into a Conda CUDA 13 environment.