Machine Learning Inference Courses and Certifications

AI Infrastructure: Deployment Types

This course provides a comprehensive guide to deploying, managing, and optimizing AI and high-performance computing (HPC) workloads on Google Cloud.

• DataCamp
• 2 hours
• Self-Paced
• Free Trial Available

Prebuilt Docker Images for Inference in Azure Machine Learning

Explore prebuilt Docker images for inference in Azure Machine Learning through a PyTorch deployment demo and scoring script.

• YouTube
• 2 hours 3 minutes
• Self-Paced
• Free Video

Production Machine Learning Systems

1036 ratings at Coursera

Design production ML systems: choose between static and dynamic training and inference, build adaptable pipelines, tune I/O and compute performance, and leverage distributed TensorFlow and TPUs.

• Coursera
• 6 weeks, 2 hours a week
• Self-Paced
• Paid Course

Coursera

Optimize TensorFlow Models For Deployment with TensorRT

77 ratings at Coursera

Optimize TensorFlow models for faster inference with TF-TRT, converting deep learning models at FP32, FP16, and INT8 precision and tuning parameters to boost throughput.

• Coursera
• 2 hours 29 minutes
• Self-Paced
• Paid Course

Pragmatic AI Labs

Hugging Face Hub and Ecosystem Fundamentals

Discover and evaluate models on the Hugging Face Hub, read model cards and licenses, stream datasets, and build inference pipelines for text, image, and audio.

• Coursera
• 2 hours 13 minutes
• Self-Paced
• Paid Course

AI Infrastructure: Deployment Types

Deploy AI and HPC workloads on Google Cloud: build AI Hypercomputer clusters on Compute Engine, configure GKE containerization and networking, and optimize inference workloads.

• Coursera
• 6 weeks, 1 hour a week
• Self-Paced
• Paid Course

Coursera

Optimize AI Inference Speed & Accuracy

Make production models run 3-5x faster: profile bottlenecks with PyTorch Profiler, apply structured and unstructured pruning, and use post-training and quantization-aware training.

• Coursera
• 3 weeks, 1 hour a week
• Self-Paced
• Paid Course

Deploy and Scale AI Models with Cloud Run

Deploy gen AI apps and machine learning models for AI inference on Cloud Run, using GPUs and integrating with data storage services.

• Coursera
• 2 weeks, 1 hour a week
• Self-Paced
• Paid Course

Edureka

Building and Scaling ML Pipelines

Build production ML pipelines: manage features with Feast, orchestrate distributed training on Kubernetes and Kubeflow Pipelines, and serve models via BentoML, KServe, canary releases and autoscaling.

• Coursera
• 4 weeks, 2 hours a week
• Self-Paced
• Paid Course

Career Certificate

Microsoft Deep Learning Engineering with Azure

Engineer the full deep learning lifecycle on Azure: implement CNNs, RNNs, and Transformers; fine-tune models with LoRA and QLoRA; scale training with DeepSpeed ZeRO; deploy containerized models.

• Coursera
• Self-Paced
• Paid Course
• 3 courses

Board Infinity

Applied Anomaly Detection with Machine Learning

Build anomaly detection systems for tabular and time-series data using Isolation Forest, autoencoders, PR-AUC evaluation, ensemble scoring, and FastAPI deployment.

• Coursera
• 2 weeks, 2 hours a week
• Self-Paced
• Paid Course

Coursera

Design, Secure & Document Multimodal APIs

Design versioned API endpoints for multimodal AI inference, add OAuth2 authentication and observability middleware, and write OpenAPI specifications enabling automated testing and client generation.

• Coursera
• 3 weeks, 1 hour a week
• Self-Paced
• Paid Course

Hardware.ai

Machine Learning Inference on Raspberry Pi Pico 2040 via Edge Impulse

Run a machine learning model on Raspberry Pi Pico using Edge Impulse, with inference on sample and sensor data plus a data-forwarder example.

• YouTube
• 22 minutes
• Self-Paced
• Free Video

Devoxx

Serverless Machine Learning Model Inference on Kubernetes with KServe

Explore KServe for Kubernetes-native ML model serving, covering integration, autoscaling, inference graphs, monitoring, and deployment strategies for efficient production use.

• YouTube
• 38 minutes
• Self-Paced
• Conference Talk

ADC - Audio Developer Conference

Inference Engines and Audio - Machine Learning in Audio Applications

Explore inference pipelines in machine learning for audio applications, including common engines, their functionality, and creating custom solutions for platforms like Cmajor.

• YouTube
• 31 minutes
• Self-Paced
• Free Video