Developers and data scientists who want to build dependable products with large language models and be able to prove that they work, rather than relying on impressive demos.
Expert level
Deep Learning and Applied AI
LLM Applications, Retrieval and Evaluation
Engineer reliable applications on top of large language models: prompting and structured output, retrieval-augmented generation, evaluation harnesses, tool-using agents, security and red-teaming, and cost, latency and quality trade-offs in production.
- 40hours of work
- 19parts
- Reviewedcapstone
- Lifetimeaccess
- LLM application design
- Retrieval-augmented generation
- Evaluation harnesses
- Agents and tool use
- AI security
- Cost and latency engineering
At a glance
Solid Python, experience with APIs (FastAPI or similar), basic machine learning and an understanding of embeddings and transformers. A hosted language-model API account with a small budget, or an open model that runs on your computer (for example through Ollama), plus Docker. Deep Learning and Applied AI at intermediate level is recommended.
Pass the quizzes and labs, then submit a capstone project. The NIBVEDA team reviews it and either accepts it or sends it back with comments you can act on.
What you will be able to do
- 01Design prompts and structured outputs and validate what a model returns
- 02Build a retrieval-augmented generation pipeline and measure its retrieval and answer quality
- 03Create an evaluation harness and use it to compare prompts, models and settings
- 04Build tool-using assistants with safe limits, and defend them against prompt injection and data leaks
- 05Balance cost, latency and quality and operate an LLM application in production
Curriculum 40 hours in 19 parts
Select a kind to highlight its parts.
Stage 1A question-answering system over your documents, with measured retrieval7 parts · 11 h
- 1Engineering with large language models: what they are and are notLesson · Short, focused reading with questions to check yourself.1 hFree
- 2Prompting and structured outputLesson · Short, focused reading with questions to check yourself.1 h
- 3Reliable structured extractionWorkshop · Follow along and build, with the steps and the traps written out.2 h
- 4Embeddings, vector search and retrieval-augmented generationLesson · Short, focused reading with questions to check yourself.1 h
- 5Build a retrieval pipeline with citationsWorkshop · Follow along and build, with the steps and the traps written out.2 h
- 6Check yourself: prompting, structured output and retrievalQuiz · Twelve questions, marked at once, with the reason behind each answer.1 h
- 7A question-answering system over your documents, with measured retrievalLab · Hands-on work. Many labs are checked automatically against what must exist.3 h
Stage 2An assistant with tools, limits and safety tests6 parts · 10 h
- 8Evaluating language model systemsLesson · Short, focused reading with questions to check yourself.1 h
- 9Build an evaluation harnessWorkshop · Follow along and build, with the steps and the traps written out.2 h
- 10Tool use and agentsLesson · Short, focused reading with questions to check yourself.1 h
- 11A tool-using assistant with safe limitsWorkshop · Follow along and build, with the steps and the traps written out.2 h
- 12Check yourself: evaluation and agentsQuiz · Twelve questions, marked at once, with the reason behind each answer.1 h
- 13An assistant with tools, limits and safety testsLab · Hands-on work. Many labs are checked automatically against what must exist.3 h
Stage 3Red-team and harden an LLM application4 parts · 8 h
- 14Prompt injection, data leaks and safe output handlingWorkshop · Follow along and build, with the steps and the traps written out.2 h
- 15Cost, latency, caching and operating an LLM applicationWorkshop · Follow along and build, with the steps and the traps written out.2 h
- 16Check yourself: security, cost and operationsQuiz · Twelve questions, marked at once, with the reason behind each answer.1 h
- 17Red-team and harden an LLM applicationLab · Hands-on work. Many labs are checked automatically against what must exist.3 h
Stage 4A cost, latency and quality trade-off study1 part · 3 h
- 18A cost, latency and quality trade-off studyLab · Hands-on work. Many labs are checked automatically against what must exist.3 h
FinishCapstone project1 part · 8 h
- 19A production-minded LLM applicationCapstone · A full project for your portfolio.8 h
What you take away
An internship certificate with your skills on it.
Made for you automatically when you finish the last part, it names the internship programme, the level and the 40 hours, lists what you showed, and carries a number and a QR code. Anyone can check it on the NIBVEDA verification page, and it shows as withdrawn there if it is ever revoked.
- Proof you completed all 40 hours of this internship programme
- An Internship badge for your profile, CV or portfolio
- Not a job, a stipend or an academic degree, and it says so
Keep building.
3 programmes in this track, from beginner to expert. Buy the learning path and save 15%.
Build practical vision and language systems with pretrained models: transfer learning for images, object detection, text classification with transformers, efficient training and a served model with tests and a latency report.
- Transfer learning
- Computer vision
- Transformers and NLP
Learn how neural networks learn by building them yourself in PyTorch: tensors, gradients, training loops, data pipelines, evaluation and convolutional networks, finishing with an image classifier you can explain and defend.
- PyTorch
- Neural networks
- Gradient descent
See all 3 programmes in Deep Learning and Applied AI Take the placement test
Quick answers.
The policies have the full detail.
Is this a real internship?
It is a virtual internship programme: a structured, self-paced course built around a real project, with checked assessments and a certificate. It is not employment, it does not carry a stipend and it is not an academic or AICTE-approved qualification. What it gives you is verified, project-based evidence of skills.
How does self-paced work?
You start when you like and move at your own speed. Each part unlocks when you finish the one before it. There are no live classes and no deadlines. Your access is shown on each programme page.
How is my work checked?
Quizzes are marked as soon as you submit them. Labs use a tick-list of tasks. Intermediate and Expert programmes finish with a capstone that the NIBVEDA team reviews and either accepts or sends back with comments.
Can I get a refund?
Please read the refund policy before you buy. It explains when a refund is possible.
Ready to start?
Rs. 1,178.82 including GST. Lifetime access. Read the first lesson free before you decide.