Catalog · Nexora

Deep Learning advanced

Transformers and Attention, Implemented Line by Line

Build a transformer from scratch: scaled dot-product attention, multi-head projections, positional encodings, KV caching and the modern variants (RoPE, grouped-query attention, RMSNorm) that make inference cheap. You will train a small model, profile it, and understand precisely where the FLOPs go.

HT Hiroshi Tanaka 4.9

$109.00

17 hours

→

Deep Learning

Deep Learning intermediate

Deep Learning with PyTorch: Fundamentals to Fine-Tuning

Autograd from first principles, then real training loops: learning-rate schedules, mixed precision, gradient accumulation, distributed data parallel, and the debugging discipline for a loss that will not go down. Finishes by fine-tuning a pretrained model on a custom dataset with a proper evaluation harness.

HT Hiroshi Tanaka 4.9

$99.00

22 hours

→

Machine Learning

Machine Learning intermediate

Recommender Systems from Scratch

Build a recommender end to end: implicit-feedback matrix factorisation, content-based retrieval with embeddings, two-stage retrieve-then-rank architectures, and the cold-start problem every real system faces. Evaluated with offline ranking metrics and an honest discussion of why they disagree with A/B tests.

HT Hiroshi Tanaka 4.9

$89.00

15 hours

→

Agentic AI

Agentic AI intermediate

Building Production Agents with LangGraph

Design agents as explicit state machines instead of prompt spaghetti. You will build a typed graph with conditional edges, add checkpointing so runs are replayable, implement retry and refinement loops, and ship an agent that degrades gracefully when a model call fails. Ends with a production deployment that handles concurrency, idempotency and observability.

PR Priya Raghavan 4.9

$89.00

14 hours

→

Career Skills

Career Skills advanced

System Design Interviews for Senior Engineers

Senior system design interviews test judgement under ambiguity, not memorised diagrams. Requirement clarification, capacity estimation, explicit trade-offs, failure modes, and narrating your reasoning so the interviewer can follow it.

NH Nadia Hussain 4.8

$89.00

12 hours

→

Agentic AI

Agentic AI advanced

Evaluation-Driven LLM Development

Shipping an LLM feature without an eval suite is shipping a rumour. Build golden datasets from production traffic, write graders that correlate with human judgement, and wire regression gates into CI so a prompt change cannot quietly degrade quality.

MA Marta Alves 4.8

$99.00

12 hours

→

Career Skills

Career Skills beginner

Writing for Engineers: Design Docs and Postmortems

Writing is the highest-leverage engineering skill nobody teaches. Structure a design doc so reviewers engage with the decision instead of the prose, run a blameless postmortem that produces real action items, and write updates that make your work legible to people two levels away.

AB Aisha Bello 4.8

$35.00

6 hours

→

Python

Python intermediate

Modern Python: Type Hints, Async and Packaging

The Python that ships in 2026: expressive type hints and generics, structural subtyping with protocols, asyncio concurrency patterns that avoid the common deadlocks, dependency management and reproducible builds, and a strict mypy configuration you can actually adopt on an existing codebase.

MA Marta Alves 4.8

$59.00

13 hours

→

Data Engineering

Data Engineering intermediate

Vector Databases and Semantic Search at Scale

How approximate nearest-neighbour indexes actually work (HNSW, IVF, product quantisation) and what you trade for speed. Metadata filtering, hybrid dense plus sparse retrieval, reciprocal rank fusion, re-indexing strategies for embedding migrations, and keeping a vector store in sync with a relational system of record.

DO Daniel Okafor 4.8

$79.00

10 hours

→

Data Engineering

Data Engineering intermediate

Data Engineering with dbt and Modern SQL

Treat analytics code like software. Layered model architecture, incremental materialisations, snapshots for slowly changing dimensions, data tests as contracts, and documentation that stays current because it is generated. Includes CI that blocks a merge when a data test fails.

NH Nadia Hussain 4.8

$79.00

14 hours

→

Deep Learning

Deep Learning advanced

Fine-Tuning LLMs with LoRA and QLoRA

Adapt a large model on a single GPU. Parameter-efficient fine-tuning, 4-bit quantisation, dataset curation and formatting, catastrophic-forgetting mitigation, and evaluation that detects when your tune made the model worse at everything else. Includes the decision framework for fine-tune versus RAG versus prompt engineering.

AR Ahmed Rahal 4.8

$119.00

13 hours

→

Machine Learning

Machine Learning beginner

Machine Learning Foundations with scikit-learn

The honest introduction: how to frame a problem, build a baseline, and know when your model is fooling you. Linear and tree-based models, proper cross-validation, leakage detection, class imbalance, and calibration. Every concept is implemented on real tabular data rather than a toy dataset.

SD Sofia Duarte 4.8

$49.00

18 hours

→