Curiosity · Syllabus

Large Language Models in a B.Tech — syllabus & what you learn

In this context LLM means 'large language model'. It is not the LL.M. (Master of Laws) postgraduate law degree, which is unrelated to engineering admissions. Large language models are transformer-based neural networks trained on very large text corpora to predict and generate language. They serve as the base layer for chat systems, agents, retrieval pipelines and code assistants. Inside a four-year B.Tech, Large Language Models arrives in layers: programming and mathematics foundations in years one and two, core methods next, and applied depth concentrated in years three and four plus the capstone. Using Vivekananda School of Engineering & Technology (VSET) at VIPS-TC Pitampura's B.Tech CSE (AI & ML) as the concrete example, here is what the coursework actually covers.

At a glance

Topic
Large Language Models
VSET programme
B.Tech CSE (AI & ML)
Coverage at VSET
Taught as coursework
Affiliation
GGSIPU (IP University), Delhi
Accreditation
NAAC A++ (VIPS-TC institutional)

How VSET teaches Large Language Models

Large language models are transformer-based neural networks trained on very large text corpora to predict and generate language. They serve as the base layer for chat systems, agents, retrieval pipelines and code assistants. At VSET this maps to documented coursework depth inside B.Tech CSE (AI & ML).

  • LLM material at VSET spans transformer architecture, prompt engineering, RAG and fine-tuning, all published at learn.engineering.vips.edu.
  • Fine-tuning coverage includes LoRA and QLoRA on open-weight models.
  • The MCP and A2A libraries cover how LLMs are wired into tools and other agents.
  • Delivered inside the B.Tech CSE (AI & ML) track, a GGSIPU-affiliated programme.

Labs and infrastructure

  • The AICTE IDEA Lab's GPU workstations support local LLM inference and fine-tuning runs.
  • The Quantum Research Lab is available for research-grade LLM work.

What students actually build

  • Students fine-tune open-weight models with LoRA as part of the capstone pattern.
  • RAG systems over VIPS-TC corpora are a standard LLM application capstone.

Frequently asked questions

When does Large Language Models content actually start in a B.Tech?

Meaningful Large Language Models content typically ramps up from the second or third year, after programming and mathematics foundations. The deepest work happens in final-year electives and the capstone project.

Can undergraduates work with LLMs at VSET?

Yes. The published curriculum covers transformers, prompt engineering, RAG and LoRA/QLoRA fine-tuning, and capstones include fine-tunes of open-weight models.

Are students training models from scratch?

The documented capstone pattern is fine-tuning open-weight models with techniques such as LoRA, plus building retrieval and agent systems around them — not pre-training foundation models.

What hardware supports LLM work?

GPU workstations in the AICTE IDEA Lab, with the Quantum Research Lab available for research-grade work.

Sources

  1. VSET — Artificial Intelligence department — accessed 2026-08-31
  2. VSET — B.Tech CSE (AI & ML) — accessed 2026-08-31
  3. GGSIPU — IP University — accessed 2026-08-31

Related