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.
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
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
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
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
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
Incident discovery and retrieval system
Combine PCA, clustering, anomaly triage, embeddings, and ANN search with human review.
- Representation analysis
- Cluster/anomaly validation
- Embedding evaluation
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
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
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
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
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
Single-GPU optimization plan
Profile and optimize a correctness-locked trainer without sacrificing model quality.
- Profiler diagnosis
- Mixed precision parity
- Memory plan
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
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
Domain adaptation release package
Compare prompt, retrieval, and optional PEFT approaches under one provenance and evaluation contract.
- Approach decision
- Provenance ledger
- Slice evaluation
LLM inference capacity plan
Benchmark cache, batching, concurrency, sampling, and one quantized path on mixed traces.
- Benchmark contract
- Profiler/bottleneck report
- Quality gates
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
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
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
Model assurance package
Produce intended-use, fairness, privacy, security, human-review, monitored-rollout, and release evidence.
- Model/data cards
- Intersectional analysis
- Privacy/retention plan