ABCDEFGHIJKLMNOPQRSTUVWXYZ
1
WeekDaySession TitleDescription
2
11Python Refresher (FAANG coding)Python essentials, idiomatic code, problem solving
3
12NumPy Deep DiveVectorization, broadcasting, performance tricks
4
13Pandas for ML IDataFrame basics, groupby, joins, merges
5
14SQL for ML EngineersAggregations, joins, window functions, cohorting
6
15EDA Lab + HomeworkExploratory analysis, visualizations, pitfalls; assignment provided
7
21Linear Algebra for MLVectors, matrices, eigen, SVD intuition
8
22Calculus & GradientsDerivatives, chain rule, Jacobian, Hessian intuition
9
23Probability EssentialsDiscrete & continuous distributions, Bayes' rule
10
24Statistics for MLHypothesis testing, confidence intervals, p-values
11
25Math Lab: Derivations & ProblemsPractice problems: linear algebra & probability for ML
12
31ML Theory – Derive gradient for logistic regression and explain convexity.Derive gradient for logistic regression and explain convexity.
13
32Linear Regression & GLMsLeast squares, regularization, GLM intuition
14
33Logistic Regression & CalibrationProbabilistic outputs, calibration, class imbalance
15
34Decision TreesGini, entropy, splitting, pruning techniques
16
35Ensemble Methods & BoostingRandom Forests, Gradient Boosting intuition (XGBoost)
17
41Classical ML LabHands-on: training pipelines + cross-validation
18
42Feature Engineering StrategiesMissing data, encoding, interactions, feature crosses
19
43Model Evaluation Deep DiveROC, PR, calibration, cost-sensitive metrics
20
44Data Preprocessing PipelinesScaling, imputation, leakage avoidance, pipelines (sklearn)
21
45Bias, Variance & RegularizationUnderfitting/overfitting, L1/L2, dropout intuition
22
51Feature + Eval LabFeature ablation, error analysis practical
23
52ML Theory – Explain bias-variance tradeoff with examples.Explain bias-variance tradeoff with examples.
24
53
ML Coding – Clean and join multi‑table log data for modeling (FAANMG style).
Clean and join multi‑table log data for modeling (FAANMG style).
25
54
Data Engineering for ML – Build a feature store architecture: online/offline sync.
Build a feature store architecture: online/offline sync.
26
55Neural Networks IPerceptron, MLPs, representation power
27
61Backpropagation & Computation GraphsAutodiff intuition, gradients in practice
28
62Activation Functions & InitializationReLU, GELU, Xavier/He init
29
63Optimization MethodsSGD, momentum, Adam, lr schedules, batch sizes
30
64DL Lab I: Train a small NNHands-on: build/train/debug NN (PyTorch)
31
65CNN BasicsConvolution, pooling, receptive field
32
71Modern CNN ArchitecturesResNet, EfficientNet concepts
33
72Transfer Learning & Fine-tuningPractical transfer learning workflows
34
73Augmentation StrategiesAugMix, CutMix, AutoAugment basics
35
74CNN Lab: Image ClassificationHands-on: transfer learning on small dataset
36
75Text Preprocessing & TokenizationNormalization, tokenizers, edge cases
37
81Classical NLP MethodsTF-IDF, n-grams, traditional pipelines
38
82Embeddings & RepresentationWord2Vec, GloVe, contextual embeddings intro
39
83RNNs & LSTMs (brief)When to use RNNs; vanishing gradients; use cases
40
84NLP Lab: Text ClassificationHands-on: build text classifier (HF or simple)
41
85ML Coding – Implement a vectorized softmax.Implement a vectorized softmax.
42
96LLMs – Design a RAG pipeline for enterprise search.Design a RAG pipeline for enterprise search.
43
91Self-Attention & Scaled Dot-ProductMechanics of attention, QKV math intuition
44
92Transformer ArchitectureMulti-head attention, FFN, positional encodings
45
93LLM Training Dynamics
Pretraining objectives, tokenizers, compute considerations. LLM evals, agent evals, guardrails
46
94Tokenization Deep DiveBPE, WordPiece, SentencePiece & subword issues
47
95LLM Lab: Fine-tuningHands-on: fine-tune a pre-trained transformer (HF)
48
101
System Design - ML – Design an LLM inference system with batching & caching.
Design an LLM inference system with batching & caching.
49
102LLMs – Explain attention mechanism and complexity optimizations.Explain attention mechanism and complexity optimizations.
50
103Prompt Engineering EssentialsPrompt patterns, chains, pitfalls
51
104Embeddings for RetrievalEmbedding models, similarity metrics
52
105Vector Databases & FAISSIndex types, ANN, scaling considerations
53
111RAG Architecture & TradeoffsRetrieval+generation pipelines, freshness, cost
54
112RAG Lab: Build a simple RAG appHands-on: vectorize docs, retrieve, generate
55
113MLOps: Pipelines & CI/CDExperiment reproducibility, pipelines (Airflow/Prefect)
56
114Model Registry & VersioningMLflow, DVC concepts; promoting models
57
115Monitoring & Drift DetectionData & concept drift, alerts, SLIs/SLOs
58
121Scaling ML SystemsBatch vs real-time, caching, sharding
59
122Deployment Lab: Serve modelHands-on: containerize + deploy a model (FastAPI)
60
123ML System Design FundamentalsRequirements, metrics, data flow diagrams
61
124Feature Store PatternsMaterialization, online vs offline features
62
125Real-time vs Batch InferenceLatency budgets, consistency tradeoffs
63
131Case Studies: Recs, Search, AdsDesign patterns and tradeoffs in production systems
64
132System Design LabMock system design interview (team activity)
65
133
System Design - ML – Design a large‑scale real‑time recommendation system.
Design a large‑scale real‑time recommendation system.
66
134
Metrics & Evaluation – Choose metrics for fraud detection under label imbalance.
Choose metrics for fraud detection under label imbalance.
67
135Capstone Proposal PresentationsTeams present proposals, feedback from instructors
68
141Full Mock: ML Theory & CodingTimed ML theory + coding mock (FAANG format)
69
142Full Mock: LLMs & RAGTimed LLM/RAG interview simulation
70
143Full Mock: ML System DesignTimed ML system design mock
71
144ML System Design Fundamentals
Deep dive: req gathering, data flows, feature pipelines, online/offline arch, latency/throughput, trade-offs. Case studies: RecSys, Ranking, Ads.
72
145Feature Stores & Data Pipelines
Feature store architecture, offline/online sync, streaming pipelines, data quality, lineage.
73
151Scaling Training: Distributed MLData-parallel, model-parallel, sharding, orchestration (Ray, Horovod), GPU/TPU basics.
74
152Model Deployment & Monitoring
Batch vs realtime serving, canaries, shadow deploy, drift detection, alerting, retraining loops.
75
153FAANMG System Design Drills
Practice FAANMG questions: Design real‑time recommendation system, LLM inference service, fraud detection pipeline.
76
154LLMs in Production
LLM serving stacks, quantization, distillation, caching, batching, routing, inference optimization.
77
155Retrieval Systems & Vector DBs
RAG architecture, embeddings, ANN search, FAISS, vector DB tuning, latency/recall tradeoffs.
78
161Agents Intro langchain to teach agents, explain what is chaining, api access - tool calling
79
162Agents in Production
Step-by-step notebook tutorials that cover ingestion, retrieval, memory, tool routing, guardrails, evaluation, observability, CI/CD, cost tracking, security, and cloud deployment for production-ready AI agents.
80
163Capstone Presentation & Feedback
81
164Capstone Presentation & Feedback
82
165Mock Interviews (FAANMG Focus)Structured mock loops: ML coding + system design + theory + behavioral.
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100