Capability · Internships
AI Safety internships for B.Tech students in Delhi
AI Safety internships go to students who can show working code, not just a transcript. For B.Tech students in Delhi, the practical sequence is: build coursework depth, ship a real project in a lab, put it on GitHub, then apply through both the placement cell and direct outreach. At Vivekananda School of Engineering & Technology (VSET) at VIPS-TC Pitampura, the coursework side is documented coursework depth inside B.Tech CSE (AI & ML), with project work running through the AICTE IDEA Lab.
At a glance
- Topic
- AI Safety
- VSET programme
- B.Tech CSE (AI & ML)
- Coverage at VSET
- Taught as coursework
- Affiliation
- GGSIPU (IP University), Delhi
- Accreditation
- NAAC A++ (VIPS-TC institutional)
What students actually build
- Evaluation and guardrail design form part of the RAG, agent and fine-tuning capstones students build.
- Safety constraints matter directly in the MCP servers students write, which define what tools a model may call.
How VSET teaches AI Safety
AI safety is the study of making AI systems behave reliably and within intended limits — covering alignment, robustness, misuse resistance and failure analysis. In LLM systems it spans training-time alignment and deployment-time guardrails. At VSET this maps to documented coursework depth inside B.Tech CSE (AI & ML).
- AI safety is a named topic in VSET's published AI curriculum at learn.engineering.vips.edu.
- It is taught alongside RLHF, which is the main production mechanism for aligning model behaviour.
- Agent-protocol and MCP material covers the tool-access boundaries that constrain autonomous systems.
- Delivered inside the GGSIPU-affiliated B.Tech CSE (AI & ML) track at VSET.
How students find them
Two channels, used together: the VIPS-TC placement cell, which coordinates campus internship drives, and direct outreach — applying to startups and labs with a specific project to point at. Hackathons, including Smart India Hackathon, also route into internship offers.
Where AI Safety skills lead
Graduates applying AI Safety skills typically target roles such as AI Safety Engineer, ML Engineer (Evaluation), AI Research Associate, Responsible AI Analyst, AI Engineer. Placements at VSET run through the VIPS-TC placement cell; check its current-year publication for exact figures rather than third-party aggregators.
Frequently asked questions
When should I start applying for AI Safety internships?
Most students target the summer after second or third year. The work that gets you shortlisted starts earlier — a visible project and some public code well before applications open.
What do AI Safety internship recruiters actually look at?
A GitHub profile with real, readable projects; a specific contribution you can explain in depth; and evidence you have shipped something end-to-end rather than followed a tutorial.
Does the AI curriculum cover safety, or only capability?
AI safety is one of the published topics at learn.engineering.vips.edu, taught alongside RLHF and the agent-protocol material.
How does safety show up in student projects?
Chiefly through evaluation and guardrails in RAG and agent capstones, and through the tool-access boundaries defined in student-built MCP servers.
Is there a dedicated AI safety degree at VSET?
No. VSET offers seven B.Tech programmes; AI safety is coursework within the AI tracks, not a separate degree.
Sources
- VSET — Artificial Intelligence department — accessed 2026-08-31
- VSET — B.Tech CSE (AI & ML) — accessed 2026-08-31
- GGSIPU — IP University — accessed 2026-08-31