Data engineering & analytics
Use LLMs to accelerate analysis (text, SQL, summaries)
Text-to-SQL, classify free text at scale, summarize reviews/tickets with LLM APIs — with validation.
~10 focused hours·intermediate
Tools: OpenAI/Anthropic APIs, LangChain, pandas, text-to-SQL, embeddings
Market relevance — share of job ads asking for this
What employers mean
You should be able to…
- Build a text-to-SQL assistant that turns a natural-language question into a validated query
- Classify free-text at scale (support tickets, reviews, survey responses) using an LLM with a fixed taxonomy
- Summarize large volumes of unstructured feedback (reviews, call transcripts) into themes with counts
- Validate LLM output against ground truth before trusting it in a report (never ship un-spot-checked numbers)
- Design prompts that return structured, parseable output (JSON) instead of free-form text
- Know when NOT to use an LLM — e.g. exact aggregation is a SQL job, not a prompt job
- Estimate and control API cost/latency for a batch job over thousands of rows
Needs first: Clean and transform data with Pandas, Integrate LLM APIs into an application
Learn — free, link-checked
The few resources that matter
Read · intermediate · 30 min · huggingface.co
Zero-shot classification
Shows how to classify free text (support tickets, reviews) at scale without labeled training data, with runnable code. — Hugging Face
Read · intermediate · 45 min · cookbook.openai.com
How to call functions with chat models
Official example where an LLM writes and executes SQL against a real SQLite database — the core text-to-SQL pattern employers ask about. — OpenAI
Build from · intermediate · 120 min · github.com
Anthropic courses
Anthropic's own hands-on notebooks for tool use, structured extraction, and grading model output quality. — Anthropic
Practice
LLM-assisted triage for Hindi/English customer support tickets
Take a public support-ticket or review dataset (or simulate bilingual Hindi/English tickets), and build a pipeline that uses an LLM API to classify each ticket into a fixed taxonomy (billing, delivery, product defect, other), extract sentiment, and summarize the top issues of the week. Validate a sample against manual labels and report accuracy.
Done when
- Pipeline processes at least 200 tickets end-to-end and outputs structured JSON per ticket
- A held-out sample of 30-50 tickets is manually labeled and compared to LLM output with a reported accuracy/agreement number
- Handles at least one mixed Hindi/English (Hinglish) input correctly
- README documents prompt design choices and estimated per-1000-ticket API cost
Prove it
Evidence a recruiter can check
- Public GitHub repo with the pipeline code, sample outputs, and a validation-accuracy report
- A comparison table: LLM classification vs. manual ground truth on the held-out sample
- Documented prompt iterations showing what changed and why accuracy improved
Interview
Questions you'll get asked
- How would you build a 'chat with your data' feature safely, so it can't run destructive SQL?
- You ask an LLM to classify 10,000 support tickets into 8 categories — how do you validate accuracy without reading all 10,000?
- What's your approach to getting reliable structured JSON output from an LLM?
- When would you use an LLM vs. a traditional NLP/regex approach for a text task?
- How do you handle hallucinated numbers when an LLM is asked to summarize a dataset?
- Describe a pipeline for summarizing 5,000 Hindi customer support chats into top 10 issues, with counts.
- How would you keep API costs under control when classifying a million rows?