JPJobPrepfull-stack interview
RoadmapsJS CompilerStar on GitHub

Career roadmap

NLP Engineer

Build systems that read, classify and generate language, and know when a fine-tuned small model beats a large one.

Time
8-11 months part-time
Entry bar
Python and some machine learning background.
Stages
5 · 25 topics
0/25 studied0%

Before you start NLP

  • Python and PyTorch basics
  • Linear algebra and probability fundamentals
  • Familiarity with the transformer architecture

Language and representation

5-7 weeks · 0/5 topics

Understand how text becomes numbers, because most NLP bugs live there.

  1. Unglamorous, and the source of most silent quality problems.

    • Normalisation, Unicode and encoding issues
    • Language detection and segmentation
    • Handling noisy real-world text
    • Regular expressions and their limits
  2. Subword tokenisation explains cost, context limits and multilingual weakness.

    • BPE, WordPiece and SentencePiece
    • Vocabulary size trade-offs
    • Token counts and non-English penalties
    • Special tokens and truncation strategy
  3. The representation underlying search, clustering and retrieval.

    Ch — Embeddings & Vector Search
    • Static versus contextual embeddings
    • Sentence embeddings and pooling
    • Similarity metrics and normalisation
    • Choosing an embedding model
  4. Attention mechanics get asked directly in almost every NLP interview.

    • Self-attention and multi-head attention
    • Positional encoding schemes
    • Encoder, decoder and encoder-decoder models
    • Context length and attention cost
  5. Often the right answer for cost and latency, and a differentiator in interviews.

    • TF-IDF and linear classifiers as baselines
    • Named entity recognition approaches
    • Rule-based extraction where appropriate
    • When simple methods win

BuildBuild a text classifier three ways — bag of words, embeddings, fine-tuned transformer — and compare honestly.

Core NLP tasks

6-8 weeks · 0/5 topics

The task types that make up almost all commercial NLP work.

  1. The most common commercial NLP task by a wide margin.

    • Single and multi-label classification
    • Class imbalance in text
    • Threshold selection and confidence
    • Weak supervision and labelling functions
  2. Turning documents into structured records is where the money usually is.

    • Entity recognition and linking
    • Relation extraction
    • Structured output from LLMs
    • Evaluating span-level accuracy
  3. Retrieval quality determines RAG quality more than any model choice.

    Ch — RAG
    • Lexical search and BM25
    • Dense retrieval and hybrid search
    • Reranking with cross-encoders
    • Chunking strategies and their impact
  4. Summarisation and rewriting, with the evaluation problems they bring.

    • Summarisation approaches and failure modes
    • Controlled generation and constraints
    • Hallucination and grounding
    • Decoding parameters
  5. A large practical gap, and a strong differentiator in many markets.

    • Cross-lingual models and transfer
    • Tokenisation penalties by script
    • Low-resource language strategies
    • Evaluation across languages

BuildShip a document extraction pipeline with a measured accuracy figure and an error analysis.

Training and adaptation

6-7 weeks · 0/5 topics

Knowing when to prompt, when to fine-tune, and when to train something small.

  1. Parameter-efficient tuning made this practical on modest hardware.

    Ch — Prompt Engineering
    • Full fine-tuning versus LoRA and adapters
    • Dataset construction and formatting
    • Hyperparameters that actually matter
    • Catastrophic forgetting
  2. Data quality dominates model choice for task-specific performance.

    • Annotation guidelines and agreement
    • Active learning for labelling budgets
    • Synthetic data generation and its risks
    • Deduplication and contamination checks
  3. How you get production latency and cost down without losing much quality.

    • Knowledge distillation from a large model
    • Quantisation and its quality cost
    • Pruning and small model selection
    • Latency and throughput trade-offs
  4. Often the right first answer. Knowing when it stops being right is the skill.

    • Few-shot and structured prompting
    • Output schemas and validation
    • Cost and latency of prompting versus tuning
    • Prompt versioning and regression
  5. The hardest part of NLP, and the part interviews probe most for rigour.

    Ch — Evaluation & Hallucination
    • Task-appropriate metrics
    • Human evaluation design
    • LLM-as-judge and its biases
    • Held-out sets and contamination

BuildFine-tune a small model to beat a large API model on one narrow task, on both cost and quality.

Production NLP

4-6 weeks · 0/5 topics

Serving text models under latency, cost and safety constraints.

  1. Throughput and latency engineering for transformer inference.

    • Batching and dynamic batching
    • GPU versus CPU inference economics
    • ONNX and inference runtimes
    • Autoscaling for spiky traffic
  2. Text pipelines have many stages; knowing which dominates is essential.

    Ch — Cost & Latency
    • Profiling a multi-stage pipeline
    • Caching embeddings and results
    • Model cascades and routing
    • Streaming responses
  3. Text distributions shift, and accuracy degrades silently.

    • Input distribution monitoring
    • Output quality sampling
    • Feedback capture from users
    • Retraining triggers
  4. User-facing language systems attract adversarial input immediately.

    Ch — AI Security
    • Prompt injection in text pipelines
    • PII detection and redaction
    • Toxicity and content filtering
    • Abuse rate limiting
  5. Text is full of personal data, which brings regulation into scope quickly.

    • PII handling in training data
    • Data retention for prompts and outputs
    • On-premises versus API trade-offs
    • Consent and purpose limitation

BuildDeploy a model behind an API with monitoring, caching and a documented latency budget.

Interview preparation

4-5 weeks · 0/5 topics

NLP interviews combine architecture depth, task design and practical judgement.

  1. Attention, positional encoding and tokenisation, asked precisely.

    • Explain self-attention and its complexity
    • Why positional encoding is needed
    • Encoder versus decoder model choice
    • Context length trade-offs
  2. Design a search or extraction system with quality and cost targets.

    • Retrieval architecture and reranking
    • Evaluation plan before building
    • Cost and latency budgeting
    • Handling failure and fallback
  3. Practical text processing and model usage rather than algorithm puzzles.

    • Implementing a retrieval pipeline
    • Writing an evaluation harness
    • Data cleaning under time pressure
    • PyTorch fundamentals
  4. When would you not use an LLM is now a standard question.

    • Fine-tune versus prompt versus classical
    • Diagnosing a quality regression
    • Building an evaluation set from scratch
    • Explaining trade-offs to product
  5. Measured results with error analysis beat model zoo demos.

    • A task with a real accuracy number
    • Error analysis and failure taxonomy
    • A distillation or cost reduction case study
    • Published evaluation methodology

BuildA public project with an evaluation report and an honest error analysis.

NLP tools on your CV

  • PyTorch
  • Hugging Face Transformers
  • spaCy
  • sentence-transformers
  • FAISS / pgvector
  • PEFT / LoRA
  • Weights & Biases

What NLP employers ask to see

  • A text task with a measured accuracy figure and error analysis
  • A fine-tuned model that beats an API model on cost and quality
  • A retrieval system with a documented evaluation set
  • A published evaluation methodology for a language task

Absorbed into the LLM boom but still distinct: search, extraction, classification and multilingual work need people who understand text beyond calling an API.

Content last reviewed 2026-08-31. Guidance only — no institute or paid placement is endorsed anywhere in this book.