AI & ML

Finetunes the NV-Generate-CTMR MR-brain diffusion UNet from user-supplied NIfTI training volumes using a wrapper that stages configs and delegates to upstream scripts.

Trains, evaluates, exports, quantizes, and runs inference for a Mask Grounding DINO model for open-set instance segmentation guided by text prompts.

Load sharded datasets (npy, Parquet, HDF5, raw binary) into distributed cuPyNumeric arrays using manual partitioning and Legate task launches.

Import object detection models from HuggingFace or NVIDIA NGC into a DeepStream pipeline with automated ONNX download, TensorRT engine build, custom parser, multi-stream benchmark, and PDF report generation.

Fine-tune HuggingFace CV, VLM, or LLM models on local NVIDIA GPUs using an NGC PyTorch container, with support for full or LoRA training, dataset handling, and optional model push to the Hub.

Train, evaluate, distill, quantize, export, and run inference for PyTorch-based TAO image classification models with support for multiple backbones.

Assesses NumPy code for cuPyNumeric migration readiness by analyzing source code against an API support manifest and GPU-scaling idioms, producing a structured verdict with per-finding reasoning.

Guides implementation of new model architectures in NeMo AutoModel through five phases: discovery, implementation, registration, validation, and testing.

Enables Megatron Fully Sharded Data Parallel in Megatron-Bridge with configuration overrides, code anchors, pitfalls, and verification steps.

Reduces peak GPU memory in Megatron Bridge training by applying expandable segments, parallelism resizing, activation recompute, and CPU offloading constraints.

Indexes Megatron Bridge recipes and recommends the best starting config based on model, GPU count, and training goal.

Score a clinical ASR manifest against a chosen NIM, produce a five-section KER leaderboard, and route the user via a post-eval decision tree.

Run Megatron-LM (MLM) and Megatron Bridge training with mock or real data, covering correlation testing, available recipes, and multi-GPU examples.

Configure and validate CPU offloading for Megatron Bridge training, including activation offloading and optimizer state offloading with HybridDeviceOptimizer.

Trains, evaluates, exports, and runs inference for FastFoundationStereo (FFS) stereo depth estimation models, a distilled variant of FoundationStereo with lower latency.

Deploy, debug, and operate the RTVI-CV 2D detection/tracking microservice and call its REST API for stream management, health checks, and metrics.

Deploy and operate the RTVI-CV-3D microservice for multi-camera 3D detection and tracking, supporting sample datasets, custom videos, and RTSP streams.

Create and modify NeMo AutoModel training and evaluation recipes, including YAML structure, builders, and execution flow.

Routes NuRec/Neural Reconstruction requests to the correct upstream NVIDIA skill (datasets, conversion, training, rendering, object harvesting, frame cleanup).

Identifies the weakest samples per ground-truth label in NVIDIA TAO VCN Classify experiments by running a Docker container that performs threshold sweep, weakness scoring, and per-lighting expansion, then surfaces top-K weak samples for downstream augmentation or relabeling.

Provides guidance for training Mixture-of-Experts models with long context windows, covering context parallelism sizing, selective recomputation, dispatcher choices, and practical patterns from recent experiments.

Provides practical guidance for training Mixture-of-Experts Vision-Language Models in Megatron Bridge, comparing FSDP and 3D-parallel approaches with lessons from recent multimodal experiments.

Validate and configure packed sequences and long-context training in Megatron-Bridge, distinguishing offline packed SFT for LLMs from in-batch packing for VLMs with correct context parallelism constraints.

Generate a Business Model Canvas with all 9 building blocks for creating, documenting, or analyzing a business model.

Generates a Startup Canvas combining a 9-section Product Strategy with a Business Model for new products, offering an alternative to the Business Model Canvas and Lean Canvas.

Analyze diverse user feedback to identify at least 3 distinct behavioral and needs-based user segments based on jobs-to-be-done, behaviors, and motivations.

Finds gaps between documented intent and actual implementation in codebases, catching bugs that generic scanners miss because they lack a model of intent.

Builds reliable browser automation skills through iterative experimentation, running an inner agent to browse sites and improving navigation instructions until tasks pass consistently.

Build a local browser agent that enforces a domain allowlist via CDP Fetch interception, using a safe_browser tool that owns the Playwright session and blocks off-domain requests.

Capture a full DevTools-protocol trace of any browser automation, bisect the stream into per-page searchable buckets, and attach a trace to an in-progress session for debugging.

Convert browser-use (Python) browser-automation scripts to Stagehand v3 (TypeScript) on Browserbase, replacing opaque agent loops with deterministic pipelines where possible.

Generates and edits images using GPT Image 2 across three modes: direct generation via OpenAI-compatible API, prompt engineering for host-native image tools, or pure prompt advisory. Includes 80+ structured templates for posters, UI mockups, product visuals, maps, slides, and more.

Persists project context across Claude Code sessions. Auto-loads project summaries on startup, tracks session progress, and saves structured state via deterministic Node.js scripts.

Ingest, index, search, edit, and generate video and audio content from files, URLs, live streams, or desktop capture.

Periodically scans Claude Code configuration for redundant, stale, or orphaned items and walks the user through a confirm-each-deletion cleanup.

Compare coding agents head-to-head on reproducible tasks with pass rate, cost, time, and consistency metrics.