Skip to content
View Shauryagulati's full-sized avatar
🌍
Exploring
🌍
Exploring
4 followers · 1 following

Achievements

Achievement: Pair Extraordinairex3Achievement: Pull Sharkx2

Achievements

Achievement: Pair Extraordinairex3Achievement: Pull Sharkx2

Highlights

  • Pro

Organizations

@EddieHubCommunity @OpenCodeEra @GrowInCommunity

Block or report Shauryagulati

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Shauryagulati/README.md

Hi, I'm Shaurya Gulati

🤖 AI Engineer - Agentic LLM Systems · Production RAG · Evals

The ASCII CRT from shauryagulati.dev — animated, rendered as text shaurya@dev — role, stack, where to find me

I build agentic AI systems, production RAG, and evaluation infrastructure, the kind of work that has to survive real traffic, not just a demo.

I care about retrieval quality, agent reliability, and whether a system actually works — which is why I build evals for the things I ship.

  • 🔭 Building: behavioral eval tooling for RAG agents, and AI systems for regulated domains
  • 🧰 Working with: Claude Agent SDK, RAG, multi-agent orchestration, evals, observability
  • 🎓 CMU — MS Information Systems Management (Business Intelligence & Data Analytics)
  • 💬 Ask me about: production RAG (hybrid search, RRF, reranking), agent tool-use, LLM-as-judge evals

🌐 Connect with Me

Portfolio LinkedIn Twitter

The portfolio has a working terminal with a RAG agent inside. Press / at shauryagulati.dev and type shaurya.

Pinned Loading

  1. ragverdict ragverdict Public

    pytest for RAG agents — behavioral audits (tool coverage, citation verification, hallucination guardrails, edge cases) with PASS/FAIL/WEAK verdicts. CI-friendly, MIT-licensed.

    Python

  2. suture-ai suture-ai Public

    AI-native operations layer for a cardiology practice: referral→outreach loop, LLM extraction with per-field evals, hybrid-RAG prior-auth, fail-closed tenant isolation.

    JavaScript

  3. eu-law-agent eu-law-agent Public

    Multi-agent RAG for EU tech/data/AI legislation — a query-planner → FAISS retrieval → cross-encoder rerank → LLM-synthesizer → reviewer loop, wrapped in a learning portal with progress tracking and…

    Python 1

  4. eyeline eyeline Public

    A free, open-source macOS teleprompter that docks under the MacBook notch, read your script while holding eye contact. 100% local.

    Swift