Corporate AI & Technology Training Catalog

Model Serving & Deployment Introduction to Model Deployment RuneLab Academy · 12 hours

The core steps for moving a trained model from notebook to production: serialization, serving via an API, container packaging, basic monitoring and rollback. For data scientists and developers new to model deployment.

12 hours

Live Course

5 modules

Model Serving & Deployment REST API and gRPC Fundamentals for Model Serving RuneLab Academy · 12 hours

Fundamentals of REST and gRPC for model services: HTTP/JSON design, OpenAPI, Protocol Buffers, streaming RPCs and performance comparison. For developers who want to pick the right protocol and build their first service.

12 hours

Live Course

5 modules

Model Serving & Deployment Synchronous vs Asynchronous Inference RuneLab Academy · 12 hours

Synchronous and asynchronous inference patterns: request-response, queue-based processing (Celery, Redis, Kafka), job polling, webhooks and async Python. For engineers designing long-running model calls that scale.

12 hours

Live Course

5 modules

Model Serving & Deployment Batch, Real-Time and Streaming Inference Fundamentals RuneLab Academy · 12 hours

A comparison of the three core inference modes: batch scoring with Spark and Airflow, REST-based real-time services and streaming inference with Kafka/Flink. For data and ML teams choosing the right mode for a business need.

12 hours

Live Course

5 modules

Model Serving & Deployment Model Serialization and Model File Formats RuneLab Academy · 12 hours

Saving models safely and portably: pickle/joblib risks, TorchScript, SavedModel, ONNX, safetensors and GGUF formats, packaging with MLflow and version compatibility. For ML engineers and data scientists.

12 hours

Live Course

5 modules

Model Serving & Deployment Model Serving Architectures RuneLab Academy · 18 hours

Model serving architecture patterns: embedded models, model-as-a-service, serverless, edge, multi-model and LLM gateway designs, and how platforms like KServe, Triton, Ray Serve and vLLM fit in. For architects and senior ML engineers.

18 hours

Live Course

5 modules

Model Serving & Deployment Latency, Throughput and Cost Trade-offs in Model Serving RuneLab Academy · 12 hours

Balancing p95/p99 latency, throughput and unit cost in model serving: dynamic batching, quantization, caching, GPU/CPU selection and load-testing optimisation. For ML and platform engineers building scalable, cost-effective inference infrastructure.

12 hours

Live Course

5 modules

Model Serving & Deployment Security for Model Serving and Inference APIs RuneLab Academy · 12 hours

End-to-end security for inference services: mTLS, OAuth2/JWT, rate limiting, safe serialization, container hardening, defence against model extraction/adversarial attacks and data privacy. For ML, platform and AppSec engineers.

12 hours

Live Course

5 modules

Model Serving & Deployment TensorFlow Model Serving Fundamentals RuneLab Academy · 12 hours

Exporting TensorFlow and Keras models as SavedModel, defining SignatureDefs and serving them over REST and gRPC with TensorFlow Serving. For data scientists and ML engineers starting to deploy TensorFlow models.

12 hours

Live Course

5 modules

Model Serving & Deployment Advanced TensorFlow Model Serving and Optimisation RuneLab Academy · 12 hours

Multi-model configurations, dynamic batching, XLA/TensorRT and mixed-precision acceleration, GPU memory tuning, Prometheus metrics and custom servables in TensorFlow Serving. For engineers operating high-traffic TF services.

12 hours

Live Course

5 modules

Model Serving & Deployment Deploying TensorFlow Serving on Docker and Kubernetes RuneLab Academy · 18 hours

Operating TensorFlow Serving at scale on Docker and Kubernetes: pulling models from object storage, GPU scheduling, readiness/liveness probes, HPA/KEDA autoscaling and KServe integration. For MLOps and platform engineers.

18 hours

Live Course

5 modules

Model Serving & Deployment TorchServe Fundamentals for PyTorch Model Serving RuneLab Academy · 12 hours

Deploying PyTorch models with TorchServe: writing custom Handlers, packaging .mar files with torch-model-archiver, using the Inference and Management APIs, and managing workers and versions. For data scientists and ML engineers using PyTorch.

12 hours

Live Course

5 modules

Model Serving & Deployment Advanced TorchServe: Workflows, Optimization and Scaling RuneLab Academy · 12 hours

Multi-model DAG workflows in TorchServe, acceleration with torch.compile/ONNX/TensorRT, multi-GPU and large-model parallel serving, custom Prometheus metrics and production security. For senior ML and MLOps engineers.

12 hours

Live Course

5 modules

Model Serving & Deployment Dynamic and Offline Batch Inference with TorchServe RuneLab Academy · 12 hours

Dynamic batching and high-volume bulk scoring in TorchServe: calibrating batch_size and max_batch_delay, writing vectorised Handlers, padding variable-length inputs and integrating queues. For ML and data engineers.

12 hours

Live Course

5 modules

Model Serving & Deployment ONNX and ONNX Runtime Fundamentals RuneLab Academy · 12 hours

Converting PyTorch, TensorFlow and scikit-learn models to ONNX, validating graphs, accelerating inference with ONNX Runtime and Execution Providers (CPU, CUDA, TensorRT) and quantization. For ML and deployment engineers.

12 hours

Live Course

5 modules

Model Serving & Deployment NVIDIA Triton Inference Server Fundamentals RuneLab Academy · 12 hours

High-performance model serving with NVIDIA Triton Inference Server: Model Repository layout, config.pbtxt, dynamic batching, concurrent model execution, HTTP/gRPC clients and Perf Analyzer. For ML and MLOps engineers.

12 hours

Live Course

5 modules

Model Serving & Deployment Advanced NVIDIA Triton: Ensembles, BLS, LLMs and Tuning RuneLab Academy · 12 hours

Automated tuning with Triton Model Analyzer, Ensembles and Business Logic Scripting (BLS), stateful/sequence batching, shared memory (IPC) and LLM serving with TensorRT-LLM/vLLM backends. For senior ML engineers.

12 hours

Live Course

5 modules

Model Serving & Deployment Integrating Multi-Framework Models with NVIDIA Triton RuneLab Academy · 12 hours

Unifying PyTorch, TensorFlow, ONNX, TensorRT, OpenVINO and scikit-learn/XGBoost (FIL) models alongside custom Python backends on a single Triton server. For ML and MLOps engineers managing heterogeneous model portfolios.

12 hours

Live Course

5 modules