# Arihant Deva — Full Site Content

> A markdown dump of every public-facing section of arihantdeva.com, formatted for ingestion by language-model crawlers and retrieval-augmented systems. Updated 2026-05-18.

---

## About

**Name:** Arihant Deva
**Tagline:** Finance + engineering.
**Location:** New Jersey, USA
**Contact:** [LinkedIn — arihant-deva-44004629a](https://www.linkedin.com/in/arihant-deva-44004629a/)

I build research and trading systems for myself, and I write equity research the rigorous way. Currently shipping **Leviathan** — an autonomous equity research platform that turns a ticker into a full DCF model, research memo, and investor deck. Looking for the next seat where research rigor and engineering throughput compound.

---

## Projects

Things I've built. Shipped, breaking, or quietly running on a server somewhere.

### Leviathan (LVT-001) — Autonomous equity research platform

**Status:** Shipping.
**Website:** [leviathanterminal.com](https://leviathanterminal.com/)

Ticker in → Excel DCF model, Word research memo, PowerPoint investor deck out.

**What ships today**

- WACC + DCF (bear / base / bull scenarios)
- Peer comps — trading and transaction multiples
- Monte Carlo simulation + historical valuation bands
- Beneish M-Score forensic accounting score
- BUY / HOLD / SELL recommendation with price target

**On the roadmap**

- M&A: accretion / dilution, synergy modelling, LBO
- Portfolio analytics: VaR, Sharpe, max drawdown, efficient frontier, factor exposure
- Multi-field screener — value / growth / quality / momentum
- Factor backtesting
- Real-time event detection (earnings, filings, insider transactions) → automatic re-analysis
- FINRA 2241 / MiFID II compliance exports
- 13F institutional ownership tracking
- Bond and credit scoring
- Private-company manual-input pipeline

**Data sources:** SEC EDGAR (XBRL), Yahoo Finance, Finnhub, Financial Modeling Prep, Alpha Vantage, and six others.

**Stack:** FastAPI · React 19 · Vite · PostgreSQL · openpyxl · python-docx · pptxgenjs · Claude API.

**Platform:** Multi-tenant. JWT authentication with organization / team / role hierarchy (Owner · Admin · Member · Viewer). Named API keys, usage metering, and quota enforcement.

---

### Jarvis (JRV-002) — Local voice agent

**Status:** Running.

Wake-word voice assistant that runs entirely on-device — no cloud round-trip.

- Voice Q&A
- `research <topic>` → generates a PDF research brief
- `suit up` → starts a soundtrack, opens leviathanterminal.com, attaches a tmux workstation
- `jarvis start / stop / status` daemon

**Stack:** Porcupine (wake word) · Silero VAD · Whisper.cpp (speech-to-text) · Ollama llama3.1:8b · Piper (text-to-speech). All local; no cloud round-trip.

---

### EasyApply (EAP-003) — Personal job-application automation

**Status:** Personal tool.

Headless browser script that fills out internship applications across LinkedIn, Handshake, and Indeed.

- `launch_persistent_context` — one Chromium profile per site
- Claude Haiku fills free-text form fields
- Short cover-letter drafting from a resume + JD prompt

**Stack:** Playwright (persistent contexts) · Claude Haiku.

Built for myself, shared with a few friends. Not a product.

---

### Inquire (INQ-004) — Tenant management platform

**Status:** Beta.

Tenant intake and triage for small landlords. Tenants submit; AI triages urgency with reasoning; landlords manage everything in one console.

- 13-table data model
- AI-triage: urgency · reasoning · tenant self-rating · admin override
- Inquiry messages and attachments
- Status events and audit log
- Password resets, debug emails, public-ref sequence
- `/portal` (tenant) · `/admin` (landlord) · `/accept-invite` · `/account` — full authentication flows with invitations

**Stack:** Next.js 16 · React 19 · Drizzle ORM · Neon Postgres · NextAuth 5 (beta) · Argon2 · Vercel.

---

## Professional Timeline

Where I've been, in chronological order — from the first ticker to the current seat.

### Early — Started trading

Got curious about markets as a teenager. Self-taught from filings, transcripts, and primary sources rather than influencers. Quiet, long, compounding interest.

### Early — Niche conviction

Built early conviction in a then-niche corner of markets. Spent years researching it before it was mainstream. Wrong often, right enough to keep going.

### Early — Drawdown → discipline

Learned the hard way that conviction without risk management is just a story. A drawdown taught more than any course. Built checklists, position-sizing rules, and a "thesis-kill" file for every position.

### School — Millburn High School

Honors coursework, AP-heavy load in math, economics, and the sciences. Where the markets habit started turning into something more structured.

### School — Investment Club, President

Ran the club, restructured the pitch process, mentored younger members on building real DCFs instead of vibes-based price targets.

### Internship — FinBotX, Quant/research intern

Worked on systematic equity signals. First time touching production-grade backtesting infrastructure.

### School — Rutgers Business School, Finance & Analytics

Dean's List. Coursework in valuation, econometrics, and accounting forensics.

### Work — Shepherd Ventures, Quantitative Researcher

Built mean-variance portfolio optimization on the S&P 100 in Python (PyPortfolioOpt · cvxpy · scipy). Layered K-means preselection, GARCH(1,1) volatility via `arch`, covariance shrinkage, and weight-bounded constraints feeding the efficient frontier. Backtested through tail events — including the COVID drawdown — against equal-weight and proportional-weight baselines. Outputs: optimized weights, drawdown curves, Sharpe-maximized portfolios.

**Tags:** PyPortfolioOpt · cvxpy · GARCH(1,1) · K-means · covariance shrinkage.

### Pivot — Independent research → Leviathan

Realized every sell-side report I read could be assembled by an agent if I gave it the right tools. Started building.

### Now — Leviathan

Institutional-grade autonomous equity research platform. See the Projects section above for the full breakdown.

### Next — Looking for the next seat

Targeting roles where research rigor and engineering throughput compound.

---

## Creative

Sticky whiteboard, in progress. Pinned tiles, half-finished thoughts.

- **Side A — Writing:** Long-form essays and short notes.
- **Side B — Field notes:** Lessons from running real money and live experiments.

More coming.

---

## Personal

Mind-map, in progress. A radial map of the off-screen me — convictions, books and reading, music, training and fitness, places, people. Coming soon.

---

## Contact

Best place to reach me is [LinkedIn](https://www.linkedin.com/in/arihant-deva-44004629a/).

---

## Site

- **URL:** https://arihantdeva.com/
- **Repository:** Static HTML + in-browser Babel React (no build step). Three.js for the home-scene WebGL.
- **Mobile:** A separate touch-first interface routes from mobile devices.
- **License:** Content © Arihant Deva. Reuse with attribution.
