GENAI · Internship domain

Generative AI

Fine-tune, prompt-engineer, and ship GenAI products.

Apply for Generative AI
By the end, you'll have shipped

a production-grade GenAI application with retrieval

Program structure

Your training passport

Every domain runs the same three-stage structure. Here's what each stage looks like for Generative AI.

STAGE 01 Week 1–2 · Training

Prompt engineering and evaluation

Weeks 1-2. You write 30+ prompts, build an eval harness, and learn to tell the difference between a model that's flaky and a model that's actually bad. Mentor scores your evals against their own.

WEEK
1–2
STAGE 02 Week 3–4 · On-the-Job Training

Retrieval and grounding

Weeks 3-4. RAG over a real corpus, chunking strategy, embedding choices, source citations in the UI. You build a chatbot for a partner's internal docs and they actually try to break it.

WEEK
3–4
STAGE 03 Month 2–3 · Development

Fine-tune or ship to production

Months 2-3. Either fine-tune a small open-weight model on a focused task, or ship a streaming chat product with cost-aware architecture (caching, batching, model selection). Both paths require a writeup.

MONTH
2–3
What Batch 1 shipped in this domain
GENAI RAG chatbot over 200+ PDF manuals with streaming UI and source citations
GENAI Tamil-English translation API using a fine-tuned NLLB adapter
GENAI Meeting-notes summariser that runs as a Slack app
Skills you'll build
  • Prompt engineering & few-shot design
  • RAG pipelines
  • Fine-tuning open-weight models
  • Evaluation of LLM outputs
  • Streaming chat UX
  • Cost-aware architecture
Courses for this domain

Once you're enrolled as an intern in Generative AI, two domain-matched courses unlock on your dashboard, alongside the two courses free to every intern.

Browse the course catalog

Ready to start?

Applications are open all year — there's no fixed intake date. Onboarding starts within two weeks of approval.

Apply for Generative AI