AI Path Finder
Free consultation

Learn AI step by step in English or Hinglish

Browse every lesson

54 lessons across 9 courses, each with a real-life example, key terms, a worked example and a quick check. Every lesson is also available in Hinglish. New words? See the AI dictionary (A to Z).

AI Foundations Path

  1. What is AI? AI vs ML vs Deep Learning vs GenAI
  2. Python basics: variables and data types
  3. Python logic: if/else, loops and functions
  4. Lists and dictionaries: storing many values
  5. Git and GitHub: saving and sharing your work
  6. Pandas: working with tables of data
  7. Averages and spread: mean, median, variance
  8. Probability and distributions
  9. Correlation vs causation, and sampling bias
  10. SQL basics: asking a database questions
  11. SQL JOINs: combining tables
  12. How machines learn: features, labels and training
  13. Two kinds of prediction: regression and classification
  14. Train/test split and overfitting
  15. Measuring models: accuracy, precision and recall
  16. What is an LLM? Tokens, context and temperature
  17. Prompting: giving clear instructions to an LLM
  18. Calling an LLM API: keys, requests and costs
  19. Building a portfolio project that gets interviews
  20. Landing the AI role: resume, applications and interviews

ML Engineer

  1. What is AI? AI vs ML vs Deep Learning vs GenAI
  2. Pandas: working with tables of data
  3. Averages and spread: mean, median, variance
  4. Probability and distributions
  5. Correlation vs causation, and sampling bias
  6. How machines learn: features, labels and training
  7. Two kinds of prediction: regression and classification
  8. Train/test split and overfitting
  9. Measuring models: accuracy, precision and recall
  10. Feature engineering: turning raw data into useful inputs
  11. Decision trees, random forests and boosting
  12. Vectors and matrices: the language of AI
  13. Gradients and gradient descent: how models improve
  14. Neural networks: layers that learn
  15. Transformers and attention: how LLMs read
  16. Training vs inference: how ML runs in production
  17. Serving a model as an API with FastAPI
  18. Docker: packaging your app so it runs anywhere
  19. MLOps: experiment tracking and model registries
  20. Monitoring models: drift and silent failures
  21. Building a portfolio project that gets interviews
  22. Landing the AI role: resume, applications and interviews

Data Engineer (AI focus)

  1. What is AI? AI vs ML vs Deep Learning vs GenAI
  2. SQL basics: asking a database questions
  3. SQL JOINs: combining tables
  4. Data modelling: designing tables for analysis
  5. Pandas: working with tables of data
  6. Data pipelines: ETL, Airflow, dbt and Spark
  7. How machines learn: features, labels and training
  8. Feature engineering: turning raw data into useful inputs
  9. Data quality: catching bad data early
  10. Embeddings and vector databases: searching by meaning
  11. RAG: letting an LLM answer from your documents
  12. Streaming data: Kafka and real-time pipelines
  13. Building a portfolio project that gets interviews
  14. Landing the AI role: resume, applications and interviews

AI Product Engineer

  1. What is AI? AI vs ML vs Deep Learning vs GenAI
  2. What is an LLM? Tokens, context and temperature
  3. Prompting: giving clear instructions to an LLM
  4. Calling an LLM API: keys, requests and costs
  5. Python basics: variables and data types
  6. Python logic: if/else, loops and functions
  7. Lists and dictionaries: storing many values
  8. Serving a model as an API with FastAPI
  9. Embeddings and vector databases: searching by meaning
  10. RAG: letting an LLM answer from your documents
  11. Evaluating AI: how to know it actually works
  12. AI safety in products: hallucinations, prompt injection and guardrails
  13. UX for AI features: designing for uncertainty
  14. Tool use (function calling): letting an LLM take actions
  15. Building a portfolio project that gets interviews
  16. Landing the AI role: resume, applications and interviews

MLOps / AI Platform Engineer

  1. What is AI? AI vs ML vs Deep Learning vs GenAI
  2. How machines learn: features, labels and training
  3. Train/test split and overfitting
  4. Training vs inference: how ML runs in production
  5. Python basics: variables and data types
  6. Python logic: if/else, loops and functions
  7. Serving a model as an API with FastAPI
  8. Docker: packaging your app so it runs anywhere
  9. Serving LLMs efficiently: GPUs, batching and cost
  10. Kubernetes: running containers at scale
  11. MLOps: experiment tracking and model registries
  12. Monitoring models: drift and silent failures
  13. Building a portfolio project that gets interviews
  14. Landing the AI role: resume, applications and interviews

LLM / Agent Engineer

  1. What is AI? AI vs ML vs Deep Learning vs GenAI
  2. What is an LLM? Tokens, context and temperature
  3. Prompting: giving clear instructions to an LLM
  4. Calling an LLM API: keys, requests and costs
  5. Tool use (function calling): letting an LLM take actions
  6. Python basics: variables and data types
  7. Python logic: if/else, loops and functions
  8. Lists and dictionaries: storing many values
  9. Serving a model as an API with FastAPI
  10. AI agents: plan, act, observe, repeat
  11. MCP: a universal plug for AI tools
  12. Embeddings and vector databases: searching by meaning
  13. RAG: letting an LLM answer from your documents
  14. Building a portfolio project that gets interviews
  15. Evaluating AI: how to know it actually works
  16. AI safety in products: hallucinations, prompt injection and guardrails
  17. Landing the AI role: resume, applications and interviews

AI Research Engineer

  1. What is AI? AI vs ML vs Deep Learning vs GenAI
  2. Vectors and matrices: the language of AI
  3. Gradients and gradient descent: how models improve
  4. Probability and distributions
  5. Train/test split and overfitting
  6. Measuring models: accuracy, precision and recall
  7. Neural networks: layers that learn
  8. Transformers and attention: how LLMs read
  9. Fine-tuning and LoRA: specialising a model
  10. Reading and reproducing research papers
  11. Building a portfolio project that gets interviews
  12. Landing the AI role: resume, applications and interviews

AI Forward Deployed Engineer

  1. What is AI? AI vs ML vs Deep Learning vs GenAI
  2. What is an LLM? Tokens, context and temperature
  3. Prompting: giving clear instructions to an LLM
  4. Calling an LLM API: keys, requests and costs
  5. Embeddings and vector databases: searching by meaning
  6. RAG: letting an LLM answer from your documents
  7. Tool use (function calling): letting an LLM take actions
  8. Python basics: variables and data types
  9. Python logic: if/else, loops and functions
  10. Lists and dictionaries: storing many values
  11. Serving a model as an API with FastAPI
  12. Enterprise AI: integration, security and compliance
  13. AI safety in products: hallucinations, prompt injection and guardrails
  14. Problem framing: should AI solve this, and how?
  15. Explaining AI to non-technical people
  16. Evaluating AI: how to know it actually works
  17. Building a portfolio project that gets interviews
  18. Landing the AI role: resume, applications and interviews

AI Product Manager

  1. What is AI? AI vs ML vs Deep Learning vs GenAI
  2. What is an LLM? Tokens, context and temperature
  3. How machines learn: features, labels and training
  4. AI literacy for decisions: build vs buy, cost and limits
  5. Prompting: giving clear instructions to an LLM
  6. Prototyping AI ideas with low-code tools
  7. SQL basics: asking a database questions
  8. Measuring models: accuracy, precision and recall
  9. Metrics and A/B testing for AI features
  10. Problem framing: should AI solve this, and how?
  11. Writing an AI product spec (PRD) with an eval plan
  12. Evaluating AI: how to know it actually works
  13. AI safety in products: hallucinations, prompt injection and guardrails
  14. Building a portfolio project that gets interviews
  15. Explaining AI to non-technical people
  16. Landing the AI role: resume, applications and interviews