AI Projects

What you'll learn:

• Tool-using agents with planning and memory
• Multi-agent workflows and orchestration
• Retrieval-augmented agents over your own data
• Evaluation harnesses for agent reliability

What you'll learn:

• Tensors, autograd and custom training loops
• CNNs, RNNs and Transformers from scratch
• Mixed-precision and distributed training
• Exporting and serving trained models

What you'll learn:

• Tokenizers and attention from first principles
• Fine-tuning with LoRA and QLoRA
• RAG pipelines and prompt engineering
• Guardrails and evaluation for LLM apps

What you'll learn:

• Image classification and detection pipelines
• Segmentation and keypoint models
• Vision transformers and fine-tuning
• Deploying vision models to the edge

What you'll learn:

• Core concepts explained from first principles
• Hands-on implementation on a real dataset
• Evaluation, tuning and common pitfalls
• Packaging and serving the trained model

What you'll learn:

• Core concepts explained from first principles
• Hands-on implementation on a real dataset
• Evaluation, tuning and common pitfalls
• Packaging and serving the trained model

What you'll learn:

• Core concepts explained from first principles
• Hands-on implementation on a real dataset
• Evaluation, tuning and common pitfalls
• Packaging and serving the trained model

What you'll learn:

• Core concepts explained from first principles
• Hands-on implementation on a real dataset
• Evaluation, tuning and common pitfalls
• Packaging and serving the trained model

What you'll learn:

• Core concepts explained from first principles
• Hands-on implementation on a real dataset
• Evaluation, tuning and common pitfalls
• Packaging and serving the trained model