Career Accelerator Courses in
Applied AI

• Week 1:
  Embeddings, vector stores, and chunking strategies

• Week 2:
  Retrieval pipelines, evaluation framework, and failure modes

• Week 3:
  Building a RAG pipeline end-to-end

• Week 4:
  Scaling RAG apps, caching, hybrid search, metadata filtering

• Week 5:
  Deployment: using simple frameworks (FastAPI, Streamlit)

• Week 6:
  Hackathon + evaluation

Learn to use LLMs in real workflows by structuring tasks, designing prompts, and building simple, reliable tools that boost speed and accuracy.

• How embeddings work and how to store them

• Designing retrieval pipelines

• Evaluating RAG applications

• Building and deploying RAG-based applications

• Understanding data handling for enterprise AI tools

• Week 1:
  Preparing datasets and understanding model selection

• Week 2:
  PEFT techniques, LoRA, adapters, training workflows

• Week 3:
  Running fine-tuning jobs on small GPUs (Colab/Databricks/AWS)

• Week 4:
  Evaluation, error analysis, prompt-post processing

• Week 5:
  Packaging the fine-tuned model for inference

• Week 6:
  Hackathon + evaluation

Learn to use LLMs in real workflows by structuring tasks, designing prompts, and building simple, reliable tools that boost speed and accuracy.

• Dataset curation and cleaning for fine-tuning

• Running PEFT workflows

• Evaluating custom models

• Exporting, packaging, and deploying tuned models

• Understanding when to fine-tune vs prompt

• Week 1:
  Deployment basics, containers, FastAPI, model serving

• Week 2:
  Latency, scaling, cost management, queues

• Week 3:
  Monitoring frameworks, logging and observability

• Week 4:
  CI/CD, testing for AI workflows, safety checks

• Week 5:
  Building end-to-end MLOps workflow

• Week 6:
  Hackathon + evaluation

Learn to use LLMs in real workflows by structuring tasks, designing prompts, and building simple, reliable tools that boost speed and accuracy.

• Model serving and scaling fundamentals

• Building APIs for AI services

• Monitoring and observability for AI apps

• CI/CD for ML pipelines

• Error tracking and guardrail design