# Harsh Sinha

> AI Engineer · Prev Founder's Office @ Multibagg AI · National Finalist IFF-FinTech Olympiad '24 · IIT Patna '27. Looking for AI Engineering roles around agents, quant, and backend.

This is a personal portfolio. Prefer [llms-full.txt](https://www.harshsinha.dev/llms-full.txt) for a complete markdown CV, or [GET /api/about](https://www.harshsinha.dev/api/about) for the same data as JSON. Multibagg AI is a previous role, not current employment.

## Profile

- [Full markdown CV](https://www.harshsinha.dev/llms-full.txt): About, experience, education, projects, certifications, and tech stack
- [JSON profile](https://www.harshsinha.dev/api/about): Same content as structured JSON
- [Human-readable site](https://www.harshsinha.dev/): Visual portfolio
- [Résumé](https://drive.google.com/file/d/1Iq1ZV_sMimkoGrNui8gR6_VP04-el2TD/view?usp=sharing): PDF résumé

## Projects

- [RecoveryOS](https://rzpy-agent-web.vercel.app): An explainable revenue-recovery system for Razorpay merchants: AI proposes one bounded action, deterministic policy guards execution, and durable workflows follow failed payments to auditable outcomes. (Razorpay AI Buildathon · verified Test Mode recovery flow)
- [LLM Trading Arena](https://the-llm-trading-arena-frontend.vercel.app): A read-only research dashboard where LLMs paper-trade the Nifty 50 under realistic constraints, with rankings, trade history, portfolio analytics and deterministic Redis-backed replay. (Frontend · Nifty 50 paper-trading arena)
- [Vritta AI](https://vritta-one.vercel.app/): A financial event-intelligence platform that organizes filings, disclosures and news into structured, traceable events with materiality and source context for Indian-equity research. (Structured event intelligence for Indian equities)
- [Instagram Creative Intelligence](https://instagram-analysis-red.vercel.app): A multi-agent analysis pipeline that ranks public Instagram posts, extracts video and audio evidence, and turns measurable creative patterns into an adaptable strategy report. (Evidence-first analysis · reports, transcripts and frame sampling)
- [LLM Trading Arena Engine](https://github.com/harshsinha-12/the-llm-trading-arena-backend): A TypeScript paper-trading engine for LLMs on the Nifty 50, with technical features, portfolio-aware risk context, Redis state and reproducible execution rules. (Backend · quantitative features and auditable simulation)
- [Go Rabbit](https://go-rabbit-sable.vercel.app): An agentic contributor assistant that scopes Go issues, scans repositories, generates and validates focused patches, and prepares draft pull requests behind explicit safety gates. (Issue → validated patch → draft PR)

## Articles

- [Building AI Agents That Know When to Stop — Markdown](https://www.harshsinha.dev/articles/building-ai-agents-that-know-when-to-stop/article.md): A practical design for bounded agent loops: finish when the work is good enough, compact before context degrades, and stop safely when progress stalls. [Human-readable article](https://www.harshsinha.dev/articles/building-ai-agents-that-know-when-to-stop).
- [Memory as the Missing Layer in Self-Improving AI Agents — Markdown](https://www.harshsinha.dev/articles/self-improving-agents-memory-missing-layer/article.md): A practical architecture for agents that turn experience into safer, measurable improvements through memory, sandboxed experimentation, evaluation, and replay. [Human-readable article](https://www.harshsinha.dev/articles/self-improving-agents-memory-missing-layer).

## Contact

- [Email](mailto:sinha.harshsep@gmail.com)
- [LinkedIn](https://www.linkedin.com/in/harshsinha12/)
- [GitHub](https://www.github.com/harshsinha-12)
- [X](https://x.com/sinhaharsh12)

## Optional

- [GitHub profile](https://github.com/harshsinha-12): Source repositories
- [RecoveryOS source](https://github.com/harshsinha-12/rzpy-agent): Repository for RecoveryOS
- [LLM Trading Arena source](https://github.com/harshsinha-12/-the-llm-trading-arena-frontend): Repository for LLM Trading Arena
- [Vritta AI source](https://github.com/harshsinha-12/Vritta): Repository for Vritta AI
- [Instagram Creative Intelligence source](https://github.com/harshsinha-12/instagram-analysis): Repository for Instagram Creative Intelligence
- [LLM Trading Arena Engine source](https://github.com/harshsinha-12/the-llm-trading-arena-backend): Repository for LLM Trading Arena Engine
- [Go Rabbit source](https://github.com/harshsinha-12/go-rabbit): Repository for Go Rabbit