Model Training & Fine-tuning Agent Skills

Predicts gene and transcript structure from a DNA sequence using the hosted Genomic Intelligence API, producing a report and JSON output.

Predicts tissue or cell-type gene expression (log TPM and TPM) from a TSS-centered DNA sequence using the hosted Genomic Intelligence G0 Expression model, conditioned on a free-text cell-type description.

Automates genome-wide association studies from genotype files to publication-ready results, running PLINK2 QC and REGENIE regression with Manhattan and QQ plots.

Launches long-running evaluation batches in isolated tmux sessions with pre-flight verification, monitoring, and post-flight analysis for unattended runs.

Reference guide for evaluating LLM-generated translations between CUDA and OpenMP, covering memory model mapping, kernel launch patterns, shared memory, atomics, and common failure modes.

Performs finite element analysis, computational fluid dynamics, thermal analysis, modal analysis, and design optimization for validating designs against physical loads and predicting product behavior.

Manages the lifecycle of large language models in production, covering model versioning, prompt management, inference optimization, and cost control.

Manages the machine learning lifecycle with experiment tracking, model versioning, reproducible runs, and deployment through the MLflow platform.

Applies physical principles to model biological systems, including protein folding, membrane transport, molecular forces, and neural signaling.

Build and deploy machine learning models with TensorFlow, covering Keras, data pipelines, and production serving.

Turns model work into a production ML system with data contracts, reproducible training, quality gates, deployable artifacts, and monitoring.

Provides guidance on using JAX for machine learning and mathematical analysis, covering core concepts, transformations, ML specifics, control flow, and parallelism.

Implements Manifold-Constrained Hyper-Connections (mHC) using Doubly Stochastic Matrices to improve deep learning stability.

Deploy and serve LLMs in production with vLLM, Ollama, TGI, and llama.cpp, including quantization and GPU optimization.

Integrates on-device and cloud machine learning into Flutter apps with TensorFlow Lite and Firebase ML Kit, covering image classification, object detection, OCR, face detection, and barcode scanning.

Filters user-generated content for safety using Google Model Armor via the gws CLI.

Guides downloading and configuring RVC voice conversion models, including HuBERT and index files, and running voice conversion scripts.

Guides feature extraction and preprocessing for time series data using aeon transformers, covering collection and series transformers with code examples.

Enforces rigorous ML modeling, feature engineering, training, and evaluation standards at principal-engineer level.

Enforces ML infrastructure, experiment tracking, reproducibility, model packaging, CI/CD, monitoring, and infrastructure-as-code standards at principal-engineer level.

Implements production LLM operations: RAG pipelines, embeddings, vector databases, fine-tuning, advanced prompt engineering, cost estimation, quality evals, semantic caching, streaming, and agents.

Orchestrates AI/ML workflows for building LLM applications, RAG systems, AI agents, and ML pipelines, covering design, integration, observability, and security.

Performs time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search using the aeon toolkit.

Simulate open and closed quantum systems with QuTiP, covering master equations, Lindblad dynamics, decoherence, and quantum optics.

Solve single- and multi-objective optimization problems with NSGA-II/III, MOEA/D, and other evolutionary algorithms, including Pareto front analysis, constraint handling, and benchmarking on standard test problems.

Track ML experiments, manage the model registry with versioning, deploy models, and reproduce experiments using MLflow's framework-agnostic platform.

Connects AI assistants to the Hugging Face Hub via MCP server tools to search models, datasets, Spaces, and papers, retrieve repository details and documentation, run compute jobs, and use Gradio Spaces as AI tools.

Self-hosted observability platform for LLM applications, providing tracing, evaluation, datasets, experiments, and real-time monitoring to debug and improve AI systems.

Compute the Equal Error Rate (EER) metric using torchmetrics for binary, multiclass, or multilabel classification tasks, with reference signatures and usage examples.

Measures distributional similarity between original GAN-generated images and their semantically manipulated counterparts using the Fréchet Inception Distance (FID) metric.

Evaluates the naturalness, speaker similarity, and real-time synthesis speed of a Mandarin speech cloning system across diverse practical application scenarios.

Quantifies audio source separation quality by computing the signal-to-distortion ratio (SDR) between ground-truth and estimated stems, with per-stem and record-level averaging.

Measures the trade-off between computation time and energy consumption in mobile edge computing by computing a weighted sum of the two objectives, given system configuration parameters and per-user task characteristics.

Quantifies how sensitive a language model benchmark's reliability and ranking stability are to specific design choices, such as the selection of scenarios, subscenarios, examples, and few-shot prompts. Use when the user has predictions and gold and needs to compute DIoR.

Evaluates the faithfulness of abstractive summaries by generating questions from summary sentences and verifying if the answers can be extracted from the source document, reporting Pearson and Spearman correlations with human judgments.

Quantifies the minimum accuracy gap needed between two models for a sampled micro-benchmark to reliably preserve their ranking, using the MDAD metric from Yauney et al. (2025).