What do I need to know before starting?

The entry expectations are listed on this page. If you are close but not quite there, tell us at application; we run short pre-course preparation material and would rather get you ready than turn you away.

Does this course include the internship?

Yes, for learners who complete the core modules and meet the mid-point assessment bar. The internship is on live client work with a supervisor and code review, and you receive a written reference describing what you actually did.

Is there a certificate?

Yes, on completion of the capstone. More usefully, you finish with deployed projects, a public repository history, and a supervisor’s reference. Those are what interviews actually turn on.

What roles does AI Engineering & Applied LLMs prepare me for?

Typical destinations are AI Application Engineer, LLM Engineer, AI Product Engineer, Backend Engineer (AI features) and Forward-deployed Engineer. The curriculum is built backwards from what those interviews and first ninety days actually require.

What do I need to know before starting?

The entry expectations are listed on this page. If you are close but not quite there, tell us at application; we run short pre-course preparation material and would rather get you ready than turn you away.

Does this course include the internship?

Yes, for learners who complete the core modules and meet the mid-point assessment bar. The internship is on live client work with a supervisor and code review, and you receive a written reference describing what you actually did.

Is there a certificate?

Yes, on completion of the capstone. More usefully, you finish with deployed projects, a public repository history, and a supervisor’s reference. Those are what interviews actually turn on.

What roles does AI Engineering & Applied LLMs prepare me for?

Typical destinations are AI Application Engineer, LLM Engineer, AI Product Engineer, Backend Engineer (AI features) and Forward-deployed Engineer. The curriculum is built backwards from what those interviews and first ninety days actually require.

Academy track16 weeks · Intermediate

AI Engineering & Applied LLMs

Name: AI Engineering & Applied LLMs
Price: 64000 INR

Build AI features that survive production, not demos that survive a slide

Apply for this trackSee the full syllabus

₹64,000or 4 monthly instalments

Duration: 16 weeks
Level: Intermediate
Effort: 12–15 hrs/week
Format: Live online + project labs

Apply now

Next cohort intake is open · instalments available

Why this track

The most in-demand role in the industry right now is not model researcher. It is the engineer who can take a language model and build something a business will pay for and rely on. That is a software engineering discipline with evaluation at its centre, and this is the track that teaches it.

16weeks of live, project-based work

8modules, each ending in something deployed

4portfolio projects, reviewed like client work

5+roles this track prepares you for

Outcomes

What you will be able to do

Design and ship an LLM-backed feature end to end, from data to deployed API
Build retrieval pipelines that return the right context, and prove it with metrics
Write evaluation suites and catch quality regressions before your users do
Design agents with scoped tools, budgets and guardrails proportional to risk
Control token cost per tenant and route between models deliberately
Explain and defend every architectural trade-off in an interview

Before you start

Entry expectations

If you are close but not quite there, tell us at application. We would rather get you ready than turn you away.

01Comfortable with Python (functions, classes, packages)
02Basic understanding of HTTP APIs and JSON
03Git fundamentals
04No machine learning background required

Tools you will use

PythonFastAPIOpenAI APIAnthropic APIOpen-weight modelspgvectorQdrantLangChainLangfuseRagasDockerGitHub Actions

Syllabus

The route, module by module

8 modules over 16 weeks. Every one ends in something deployed to a real URL and reviewed line by line.

- How transformers behave from a builder's point of view
- tokenisation and context windows
- temperature, sampling and determinism
- the difference between a demo and a product
- Structured outputs and JSON schemas
- system design of a prompt
- versioning prompts like code
- few-shot vs instruction
- failure taxonomies
- Chunking strategies
- embeddings
- vector and hybrid search
- reranking
- citation and grounding
- freshness and permissions-aware retrieval
- Building a graded test set
- automatic and LLM-as-judge metrics
- regression runs in CI
- tracing
- detecting silent quality drift
- Function calling
- tool design and scoping
- planning loops and their failure modes
- idempotency, dry-run and confirm
- budgets, timeouts and tracing
- When fine-tuning is worth it
- dataset construction
- LoRA and parameter-efficient methods
- serving open-weight models
- the real cost comparison
- Latency budgets
- caching
- model routing and fallbacks
- rate limiting
- prompt injection and data exfiltration defences
- privacy and residency
- A full AI feature with retrieval, evaluation, cost metering and a deployed interface, reviewed as if it were client work

Portfolio

What you will have built

01A document assistant with citations over a real corpus
02An extraction pipeline with a graded evaluation suite
03A tool-using agent with budgets, confirmation steps and tracing
04Capstone: a deployed AI product with per-user cost metering

Where it leads

Roles this prepares you for

AI Application EngineerLLM EngineerAI Product EngineerBackend Engineer (AI features)Forward-deployed Engineer

Questions

Before you apply

The programme runs 16 weeks and expects 12–15 hrs/week including project work. Live sessions are scheduled outside standard office hours and recorded, so working professionals can keep a full-time job while studying.