About Work The Lab Experience Honors Contact
GitHub LinkedIn X

Bhopal, India — Open to collaboration

Hi, I'm Simarjot. AI/ML researcher, quant analyst, founder.

I split my time three ways: researching AI safety and guardrail systems, analyzing markets and building trading systems, and founding products end-to-end as a solo developer. I like problems with a clear, measurable definition of "working" — a benchmark, a P&L, a deploy that doesn't fall over.

AI / ML Research Quantitative Analysis Founder & Full-Stack

// who's writing this

I'm a researcher, analyst, and builder based in Bhopal, India — currently splitting my time across an equity research internship, an HR and operations role, independent AI safety research, and a self-founded product. I'm not specialized into one lane yet, and that's deliberate: I want to know what a market, a model, and a codebase each look like from the inside before I pick where to go deep. If you're working on something interesting in any of those directions, I'd like to hear about it.

0 internships & research roles
completed or in progress
0 open-source research paper
co-authored, SAID Laboratory
0 independent trading & ML
research projects, self-directed
0 place, INFOSPARK 2526
time-constrained build hackathon

Selected work

Four lanes,
one way of thinking.

Research, markets, models, and product — different domains, same approach: understand the system, find where it breaks, build something that holds.

Quantitative finance 2024 – 2025

Algorithmic Trading System Development

Designed, implemented, and backtested algorithmic trading systems for crypto futures and prediction markets in Python — signal-generation modules, a full backtesting framework for strategy P&L, and risk controls built from first principles.

  • Independent research into market microstructure & statistical arbitrage
  • Risk management: position sizing, drawdown limits, exposure caps
Play the risk simulator
AI safety research SAID Laboratory · 2026

SENTINEL — Guardrails for Web-Agent LLM Services

Co-developed an open-source, model-agnostic guardrail framework — five enforcement layers wrapping any OpenAI-compatible endpoint to block jailbreaks and prompt injection without retraining the model.

  • 49.2% of attacks blocked pre-generation at 5.0% false-positive rate
  • Llama 3.1 8B end-to-end: true attack success rate 19.8% → 9.5%
View on GitHub
Founder & full-stack Pre-seed startup · 2024–25

AI-Powered B2B SaaS

Architected, built, and deployed a full-stack AI product end-to-end as sole developer — every line hand-written, zero no-code tools — owning product design, feature prioritization, and the deployment pipeline.

  • Sole developer: design, build, ship, deploy
  • Zero no-code dependency — fully hand-coded
AI / ML research Independent · 2024–25

Custom LLM Development via Dataset Training

Fine-tuned large language models through custom dataset-training pipelines — studying training dynamics, distribution shift, and failure modes, and building end-to-end research infrastructure with Python and the broader ML tooling ecosystem.

  • Built production-style research infra end-to-end, solo
  • Studied model behavior under distribution shift

The lab — two things you can actually try

Don't take my word for it.

Two small interactive pieces pulled from the work above — a guardrail you can try to break, and a trading desk you can try not to blow up.

Try to get past the guardrail

A simplified client-side re-creation of SENTINEL's 5-layer pipeline. Type a prompt, or use a preset, and watch it move through the same enforcement logic from the paper.

L2Normalize
L3Context
L1Intent
L4Model
L5Output
>

// pipeline idle. waiting for input.

Try:

Full paper results: 49.2% of attacks blocked pre-generation at 5.0% false-positive rate · read more →

Run the desk for ten rounds

Each round, choose how to size your position before you see the outcome. Same setup every time, real tradeoffs — this is what the "Algorithmic Trading" project above is actually about.

EQUITY $10,000 +0.00%
ROUND0 / 10
STREAK
MAX DD0.0%
STATUSReady

Round 1 — the setup

Win probability 50% Payoff if you win 1.8× risk Loss if you lose 1.0× risk

Each round has different odds and payoffs — read the setup before you size your position. Survive all 10 rounds without your equity dropping below 15% of where you started.

Where I've worked

A working timeline,
not a résumé bullet list.

May 2026 — Jun 2026

Equity Research Intern

Millennium Money Finance · Remote · BSE/NSE-registered

Hands-on exposure to demat account workflows, DuPont analysis, and technical analysis of listed equities. Completed under direct mentorship with a final practical assessment.

May 2025 — Present

Human Resource Intern

Simtrak Solutions · ADORE · Remote

Selected for a structured mentorship program. Manage daily reporting and task workflows, coordinate cross-team efforts across a distributed team.

May 2025 — Jun 2025

Content Writing Intern

InAmigos Foundation · Remote

Received a Certificate of Appreciation and a Letter of Recommendation from Founder & CEO Mr. Govind Shukla for contributions to the internship department.

Apr 2025 — May 2025

Content Writing & Marketing Intern

Kshitiksha Foundation · ISO 9001:2015 NGO · Remote

30-day internship graded 'S' — Superior, the highest performance tier. Received a Certificate of Experience and a Letter of Recommendation from the Executive Director.

Toolbox

What I actually use.

Languages

  • Python
  • Java
  • HTML / CSS / JS

AI / ML

  • PyTorch ecosystem
  • Hugging Face Transformers
  • LLM fine-tuning & evaluation
  • Adversarial robustness
  • NLP

Quantitative Finance

  • Algorithmic trading
  • Backtesting
  • Statistical arbitrage
  • Risk management
  • Equity research (DuPont & technical analysis)

Building

  • Full-stack product dev
  • Deployment pipelines
  • Solo-founder execution
  • Research infrastructure

Honors & leadership

Outside the codebase.

1st

INFOSPARK 2526 Hackathon

Time-constrained technical build challenge — DPS Kolar Road, Bhopal (2025)

1st

Mount Carmel Declamation

Mount Carmel Literary Fest 2025–26

Harvard MUN India 2025

Debate Club Leader — represented a nation in committee, Bangalore

Founder, Chess Club

Billabong High International School — built the club from scratch; 100+ hours coaching Grade 5–6 students

S

Kshitiksha Foundation

'S' — Superior internship performance grade, highest tier awarded

ThinkStartup Program

IIT Delhi (RNI Park) — certified by TIDES Business Incubator, IIT Roorkee (May 2026)

Education

Billabong High International School, Bhopal

ICSE, Science + Computer Applications · 2025–2026

Coursework: Physics, Chemistry, Biology, Computer Science

Get in touch

Open to collaboration.

Whether it's AI safety research, quant & markets, or building something from zero — if it's interesting, I want to hear about it. Always happy to chat about internships, research, or just trading notes.