20 production assignments · 1 capstone

Prove the system, not just the notebook.

Every assignment asks for machine-checkable invariants, operational evidence, and a self-review. Record an attempt before revealing the reference resolution.

01Foundations

Reproducible baseline package

Design a Docker-only workflow that validates data, trains, evaluates, serializes, performs golden inference, and emits complete lineage.

  • Run manifest and data contract
  • Raw-input golden parity test
  • Failure and retry runbook
Open rubric
02Foundations

Late-delivery evaluation contract

Specify a cutoff-safe target, validation design, cost/capacity threshold, calibration report, uncertainty, and controlled experiment.

  • Decision and metric contract
  • Leakage-safe split tests
  • Threshold and calibration analysis
Open rubric
03Foundations

Point-in-time feature system

Design a versioned training set and online lookup from transaction, account, and outcome events.

  • Contracts and lineage
  • Temporal join specification
  • Late-event/backfill policy
Open rubric
04Classical ML

Explainable ticket-routing baseline

Compare linear/logistic regression, Naive Bayes, kNN, and SVM under one evaluation and serving contract.

  • Preprocessing parity
  • Model-family comparison
  • Calibration and cost policy
Open rubric
05Classical ML

Rare-fraud ensemble decision system

Compare a tree, forest, gradient boosting, and XGBoost with temporal validation and operational thresholding.

  • Ensemble ablations
  • Cost and capacity analysis
  • Calibration and explanations
Open rubric
06Classical ML

Incident discovery and retrieval system

Combine PCA, clustering, anomaly triage, embeddings, and ANN search with human review.

  • Representation analysis
  • Cluster/anomaly validation
  • Embedding evaluation
Open rubric
07Classical ML

Regional demand forecast

Build a 24-hour pipeline with naive, statistical, and boosted baselines plus interval forecasts.

  • Forecast contract
  • Rolling-origin evaluation
  • Horizon and coverage report
Open rubric
08Classical ML

Hybrid catalog ranker

Specify BM25 plus learned retrieval, ranking, re-ranking, temporal evaluation, and a versioned online path.

  • Exposure-aware data contract
  • Candidate recall analysis
  • Ranker and NDCG report
Open rubric
09Deep learning

Network from first principles

Specify a NumPy MLP, finite-difference checks, PyTorch parity, calibrated inference, and debugging report.

  • Forward/backward derivation
  • Gradient check plan
  • Optimizer/regularization ablations
Open rubric
10Deep learning

Rare-defect vision system

Design grouped evaluation, transfer learning, calibration, batch-one export, and camera-drift monitoring.

  • Grouped split and audit
  • Transfer-learning ablations
  • PR and calibration report
Open rubric
11Deep learning

Causal stateful risk model

Specify an LSTM with temporal splits, masking, BPTT diagnostics, and replay/online state parity.

  • Causal sequence dataset
  • Baseline and recurrent comparison
  • Gradient/state diagnostics
Open rubric
12Training systems

Single-GPU optimization plan

Profile and optimize a correctness-locked trainer without sacrificing model quality.

  • Profiler diagnosis
  • Mixed precision parity
  • Memory plan
Open rubric
13Training systems

Fault-tolerant distributed trainer

Specify DDP correctness, scaling experiments, worker failure, and complete checkpoint recovery.

  • Gradient/data equivalence
  • 1/2/4-GPU efficiency report
  • Kill-and-resume proof
Open rubric
14Transformers

Decoder-only transformer from scratch

Specify tokenizer, attention blocks, causal training, unit tests, sampling, and KV-cache parity without a transformer module.

  • Shape/mask tests
  • Tiny-batch overfit
  • Held-out evaluation
Open rubric
15Transformers

Domain adaptation release package

Compare prompt, retrieval, and optional PEFT approaches under one provenance and evaluation contract.

  • Approach decision
  • Provenance ledger
  • Slice evaluation
Open rubric
16Transformers

LLM inference capacity plan

Benchmark cache, batching, concurrency, sampling, and one quantized path on mixed traces.

  • Benchmark contract
  • Profiler/bottleneck report
  • Quality gates
Open rubric
17Production

Local mini ML platform

Specify idempotent events, a point-in-time join, shared feature definition, quality gates, lineage, and model registration.

  • Data contract
  • Late-event semantics
  • Feature parity design
Open rubric
18Production

Production inference contract

Specify a typed service with warmup, batching, resilience, load testing, rollout, metrics, and fallback.

  • API/artifact contract
  • Capacity/load report
  • Failure injection
Open rubric
19Production

Launch analysis and incident response

Analyze a synthetic launch, verify assignment, estimate effects, inspect slices, and choose continue, pause, or rollback.

  • Experiment validity report
  • Layered reliability diagnosis
  • SLO and runbook
Open rubric
20Production

Model assurance package

Produce intended-use, fairness, privacy, security, human-review, monitored-rollout, and release evidence.

  • Model/data cards
  • Intersectional analysis
  • Privacy/retention plan
Open rubric
Cumulative capstone

Catalog quality + multimodal marketplace search.

Open the capstone brief