Winter internship · Pre-final year · Applications open

Solumn AI Winter Internship

Evaluating the safety of frontier AI systems.
Six weeks on live AI-safety, cyber-security and model-alignment work, with a pre-placement offer on merit at the close.

6 weeksFrom 30 November 2026
₹1,00,000Fixed stipend for the period
RemoteA member of the team
Full-timePPO offered on merit

The work

Six weeks on one live deliverable.

You own one live deliverable, start to finish. Nothing here is a teaching exercise: what you build is reviewed, graded and shipped — the evaluations a frontier lab clears before it ships.

01

AI safety evaluation

Tool-use and MCP safety evaluations that measure how an agent behaves under realistic attack conditions.

02

Cyber security

Vulnerability find-and-fix tasks built from real CVEs, backed by executable verification.

03

Model alignment

Agentic environments and deterministic graders for how a model holds the line under pressure.

What you walk away with

Real work, years early.

You build the evaluations a frontier lab clears before it ships — work most engineers encounter years into a career, if at all.

01

A pre-placement offer

Extended on merit at the close, at compensation benchmarked to frontier AI research roles.

02

The craft, early

Reviewed work, direct feedback and real depth in agentic safety, security and alignment.

03

Paid, and remote

₹1,00,000 for the six weeks, worked remotely, full-time over the winter.

Who can apply

Pre-final-year students at the IITs.

B.Tech · Dual Degree · M.Tech — CSE, AI/ML, Data Science, ECE, EE, Mathematics & Computing

Confident you can contribute in this space? Apply regardless of branch.

Selection process

Send your CV and a few lines on your strongest work.
Shortlisted applicants get a short, real task.
A conversation with the team about what you built.
We review and respond on a rolling basis, ahead of the 30 November start.

Apply.

A few details and your CV. We review on a rolling basis and reach out to shortlisted candidates ahead of the start.

1. Your details

2. Your course

3. Your work

Links to your strongest work: repositories, papers, CVEs, datasets, CTFs or past projects.

4. Start