Machine learning & data science

Solve NLP tasks (classification, NER, similarity)

Tokenization, transformers via Hugging Face, fine-tune small encoders for classification/NER.

~20 focused hours·intermediate

Tools: Hugging Face Transformers, spaCy, tokenizers, scikit-learn

Market relevance — share of job ads asking for this
Prerequisite capability — not asked for directly, but needed for others.
What employers mean

You should be able to…

  1. Tokenize and preprocess text correctly for a transformer model (truncation, padding, special tokens)
  2. Fine-tune a small pretrained encoder (BERT/DistilBERT) for text classification
  3. Build a Named Entity Recognition (NER) model for a domain-specific entity set
  4. Compute text similarity/embeddings for search or deduplication
  5. Handle multilingual or code-mixed text (e.g. Hindi, Hinglish) preprocessing challenges
  6. Evaluate classification/NER with the right metrics (F1, precision/recall per class, not just accuracy)
  7. Know when a classic ML baseline (TF-IDF + logistic regression) beats a transformer for a small dataset

Needs first: Train and evaluate classical ML models

Learn — free, link-checked

The few resources that matter

Practice

Hindi/Hinglish support-ticket classifier and entity extractor

Collect or synthesize a small labeled dataset of Hindi/Hinglish customer support tickets. Build a TF-IDF baseline classifier, then fine-tune a small multilingual encoder (e.g. mBERT or IndicBERT) for the same classification task and compare. Additionally extract key entities (product name, order ID) with a NER model or rule-based fallback.

Done when
  • Labeled dataset (100+ examples) with a documented labeling scheme and train/test split
  • Both TF-IDF baseline and fine-tuned transformer trained, with F1 per class compared in a table
  • NER or entity extraction component demonstrated on at least 10 example tickets with correct/incorrect cases shown
  • README honestly states which approach won and why, including any code-mixing failure cases found
Prove it

Evidence a recruiter can check

  • Public GitHub repo with dataset (or synthetic generation script), training code and eval notebook
  • Per-class F1 table comparing baseline vs transformer model
  • Model card or short doc listing known failure modes on code-mixed input
  • Can explain live the tokenization/preprocessing choices made for Hindi/Hinglish text
Interview

Questions you'll get asked

  1. How would you build a classifier to route support tickets into 5 categories, and what would you try first?
  2. Walk me through fine-tuning BERT for a classification task -- what changes vs training from scratch?
  3. How do you evaluate a NER model, and why isn't accuracy the right metric?
  4. What challenges come up with Hindi or Hinglish (code-mixed) text that don't come up in English?
  5. When would a TF-IDF + logistic regression baseline be a better choice than fine-tuning a transformer?
  6. How do you handle class imbalance in a multi-class text classification problem?
  7. What's the difference between a tokenizer's vocabulary and the model's embedding layer?