Introduction

Preparing for AI/ML roles can be overwhelming due to the vast amount of topics to cover. To stay organized, I created a structured roadmap that covers fundamental concepts from classical ML to Generative AI. Here’s my checklist, which helped me stay on track.

Roadmap for AI/ML Interviews

1. Mathematics for ML
2. Classical Machine Learning
3. Multi-Layer Perceptrons (MLP)
4. Deep Neural Networks (DNN)
5. Natural Language Processing (NLP)
6. Computer Vision (CV)
7. Generative AI (GenAI)
8. Model Evaluation & Training Techniques
9. Final Interview Preparation

---

Mathematics for ML

• Linear Algebra
  • Vector spaces
  • Eigenvalues/Eigenvectors, Orthogonal Eigenvectors
  • Matrix decompositions (SVD, PCA)
• Probability and Statistics
  • Bayes’ theorem
  • Naïve Bayes
  • Gaussian Distributions
  • KL Divergence
  • Entropy
• Optimization
  • Gradient Descent (SGD, Adam, RMSprop)
  • Convex Optimization
  • Lagrange Multipliers
• Calculus
  • Differentiation
  • Chain Rule
  • Hessian Matrices
  • Jacobians

Classical Machine Learning

• Overfitting, Underfitting, and Regularization
  • L1 Regularization
  • L2 Regularization
  • Dropout (relation with L1 and L2)
• Bias-Variance Tradeoff
• Feature Engineering
• Supervised vs. Unsupervised Learning
• Common ML Algorithms
  • k-NN
  • SVM
  • XGBoost
  • Random Forests
  • Naïve Bayes
  • Decision Trees
  • Gini Index

Multi-Layer Perceptrons (MLP)

• Perceptron Model, Learning Rule, XOR Problem
• Activation Functions: ReLU, Sigmoid, Tanh, Softmax
• Backpropagation, Chain Rule, Weight Updates
• Batch Normalization, Dropout
• Vanishing and Exploding Gradient Problem

Deep Neural Networks (DNN)

• CNNs (Filters, Pooling, Architectures: AlexNet, VGG, ResNet, EfficientNet)
• Transfer Learning, Fine-Tuning, Normalizations
• Residual Connections, 1x1 Convolutions
• RNN, LSTM, GRU: Vanishing Gradients, Gated Mechanisms
• Attention Mechanisms, Transformers (Self-Attention, Multi-Head Attention)

Natural Language Processing (NLP)

• Basic NLP Preprocessing
  • Tokenization, Lemmatization, Stemming, Stop-word Removal
• Word Embeddings
  • Word2Vec (CBOW, Skip-Gram), GloVe, FastText
  • Transformer-based embeddings
• Sequence Models
  • RNNs, LSTMs, GRUs (gates) and need of BERT
• NLP Tasks
  • Named Entity Recognition (NER), Part-of-Speech (POS) Tagging
  • Sentiment Analysis, Machine Translation

Computer Vision (CV)

• CNN Architectures: ResNet, MobileNet, EfficientNet, Residual Connections
• Object Detection: YOLO, Faster R-CNN, SSD
• Non-Maximum Suppression (NMS) in Object Detection
• Image Segmentation: U-Net, R-CNNs family, Semantic vs. Instance vs. Panoptic Segmentation, RoIPooling
• Generative Models for Images: GANs, Autoencoders

Generative AI (GenAI)

• GANs: Vanilla GAN, DCGAN, StyleGAN, CycleGAN
• Variational Autoencoders (VAEs) and Latent Representations
• Transformers & LLMs: Basic architecture, GPT-series, LLaMA, Mistral
• Diffusion Models: DALL-E, Stable Diffusion
• Transformer Models in GenAI: ViT, Transformer-XL
• Types of Attention Mechanisms: Self-Attention, Multi-Head Attention, Cross-Attention, Group Query Attention
• Optimization Techniques for Attention: FlashAttention, Sliding Window Attention, Linformer
• Other quite asked topics : Positional encodings, RPE, layernormalization, RMS Norm, SwiGLU

Model Evaluation & Training Techniques

• Evaluation Metrics
  • Accuracy, Precision, Recall, F1-score, MAE, MSE, cosine similarity
  • ROC-AUC Curve, PR Curve, perplexity score, BLUE score
• Validation Techniques
  • Train-Test Split, Cross-Validation (k-Fold, Leave-One-Out)
  • Bootstrapping
• Famous Training Techniques
  • Early Stopping, Learning Rate Scheduling
  • Data Augmentation, Transfer Learning
  • Hyperparameter Tuning (Grid Search, Random Search, Bayesian Optimization)

Final Preparation

• Common pitfalls in ML model deployment
  • Overfitting
  • Data Leakage
  • Model Interpretability
• System Design for AI Applications
• Coding Challenges for ML/AI Roles
  • Implementing ML Algorithms from Scratch
  • Data Structures & Algorithms (DSA)

---

Conclusion

This checklist helped me cover essential topics in a structured manner while preparing for AI/ML roles. If you’re on the same journey, feel free to use this as a reference and tailor it to your needs!

Hello! I’m Himanshu Upreti, a Machine Learning Engineer at Google based in Bangalore, India. Previous to that I have experience of AI Engineer in Intel and Qualcomm. I was born in the beautiful state of Uttarakhand, India.

About Me

I hold a Master’s degree in Computer Science and Engineering from the prestigious Indian Institute of Technology Bombay (IIT Bombay). With a strong passion for technology and innovation, I’ve been actively contributing to various projects and research in the field of computer science.

My day-to-day work involves tackling exciting challenges in Natural Language Processing (NLP), Computer Vision (CV), and Machine Learning (ML). I am deeply interested in optimizing and deploying models using ONNX, leveraging the power of Git for version control, and exploring the capabilities of PyTorch for advanced research. I’m also proficient in C++, Python, and other technologies that help me create efficient and scalable solutions.

Work Experience

During my time at Intel Bengaluru, I have been involved in development of pytorch-distributed modules for Intel’ Gaudi accelerators.

During my time at Qualcomm CR&D, I’ve been involved in cutting-edge projects of AI100 that push the boundaries of cloud technology. My expertise includes:

• Developing and optimizing advanced algorithms in C++ to optimize neural networks.
• Optimizing source code of SOTA neural network for optimized peformance on AI100
• Designing and developing Graph Neural Networks projects
• Leading cross-functional teams to deliver successful projects.
• Designing optimized solutions to showcase Qualcomm’s performance in MLPerf.
• Collaborating with researchers and engineers to drive innovation and improvements in Qualcomm’s AI100 SDK.

Education

• Master of Technology (M.Tech) in Computer Science and Engineering

  • Indian Institute of Technology Bombay (IIT Bombay)

• Bachelor of Technology (B.Tech) in Computer Engineering

  • GB Pant University of Agriculture and Technology (GBPUAT)

Location

I am currently based in Bangalore, India, where I enjoy being part of a vibrant tech community and contributing to the city’s technological advancements.

Hobbies and Interests

Outside of my professional life, I have a passion for photography. Capturing moments and telling stories through images has always fascinated me. You can find some of my photography blogs.

I also believe in the importance of staying fit and active. In my free time, you’ll often find me at the gym, where I engage in various physical activities to maintain a healthy lifestyle.

Thank you for visiting my portfolio page. If you have any inquiries or would like to connect, feel free to reach out!

Follow me on LinkedIn for updates and insights into my work. You can book a 1:1 session with me on Topmate