Developer track · Months 4–6

Build the intelligence.

Learn to build, operate and evaluate practical AI systems.

Basic Python needed; a free refresher is included.

Modules

Six modules, weekly labs, one capstone.

The Developer track follows the shared foundation in months 2–3 and carries 20 of the programme’s 60 proposed credits.

  1. 01Python for AI3 credits
  2. 02AI Dataset Creation & Curation4 credits
  3. 03LLM APIs & RAG4 credits
  4. 04AI Agents & Tool Use3 credits
  5. 05Agent Operations, Review & Policy Compliance3 credits
  6. 06Deployment, Evaluation & Safety Testing3 credits

Outcomes

What you’ll gain

  • Build and label high-quality AI datasets
  • Operate, monitor and review AI agents
  • Test agents against safety and policy rules

You’ll build

A curated dataset and a reviewed AI agent, deployed with a public link for your portfolio.

Career pathways

Where this track can lead.

Career pathways show the kinds of roles the programme prepares learners for. They are not guaranteed job outcomes.

AI data & agent operations

Create and curate AI data; run, review and govern AI agents.

  • AI Dataset Creator
  • AI Dataset Builder
  • AI Agent Operator
  • AI Agent Reviewer
  • AI Agent Policy Reviewer

AI engineering

Build, evaluate and secure AI applications and agents.

  • AI Developer
  • Generative AI Engineer
  • LLM Engineer
  • AI Agent Engineer
  • AI Evaluation Engineer
  • AI Safety Engineer

Before you specialise

Months 1–3 are shared by both tracks.

Fundamentals of Computing in month 1, then ai foundations for all: common to developer and business tracks, before learners specialise.

  • How AI, machine learning and LLMs really work
  • Prompt engineering and AI productivity
  • Working with data using AI
  • AI ethics and responsible use
  • AI governance, policy and data privacy
  • AI safety and alignment fundamentals

Example projects

The kind of work you’ll do.

AI Agents

Developer track

A support agent that knows when to hand over

Problem
Routine support questions pile up, but a fully automatic bot creates risk on the hard ones.
Approach
An agent with tool access for lookups, clear policy rules, and an escalation path to a human reviewer.
Outcome
A deployed, reviewed agent with a public demo link and a written policy review.
Technology
PythonLLM APITool callingPolicy checks

RAG Systems

Developer track

Answers grounded in your own documents

Problem
Teams lose time searching scattered manuals, circulars and policies.
Approach
Index the documents, retrieve the relevant passages and generate answers that cite their sources.
Outcome
A searchable assistant with citations and an evaluation set of real questions.
Technology
PythonEmbeddingsVector indexLLM API

Voice AI

Developer track

A bilingual voice assistant for first-line queries

Problem
Many callers prefer to speak, and in Hindi as often as English.
Approach
Speech-to-text, an LLM with a narrow, well-tested scope, and speech output, with safe fallbacks.
Outcome
A prototype voice flow tested against a scripted set of real caller questions.
Technology
Speech-to-textLLM APIText-to-speech

Prefer the other path?

Explore the Business track

Admissions

Five steps to your first class.

Weekday (Mon, Wed, Fri) or weekend (Sat, Sun) batches, 18 hours a month. EMI is available for the paid course.

  1. Step 01

    Register

    Tell us about yourself through the short registration form.

  2. Step 02

    Choose your track

    Developer or Business, and a weekday or weekend batch.

  3. Step 03

    Counselling

    A free one-to-one session to check fit and answer your questions.

  4. Step 04

    Complete admission

    Confirm your place in the paid course. EMI is available.

  5. Step 05

    Begin the programme

    Start with Fundamentals of Computing in month one.

Your AI career doesn’t start with a job. It starts with capability.

Build the foundations. Learn the systems. Work on real problems.

Questions? Call +91 84476 13585 or write to admin@krimkar.com.

Free CounsellingApply Now

Apply for Bihar AI Launchpad