Skip to content
View nitin3150's full-sized avatar

Block or report nitin3150

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
nitin3150/README.md

Hi 👋 I'm Nitin

AI Engineer | LLM Agents · Evals & Guardrails · RAG
MS in Artificial Intelligence @ Northeastern University  |  Founder @ AgentSentinel


🚀 About Me

I build AI systems that work in production — not just in notebooks.

  • 🛡️ Founder of AgentSentinel — open-source LLM agent governance platform (evals, guardrails, adversarial testing) · pip install agentsentinel-ai
  • 🔬 Focused on LLM evaluation, runtime guardrails, RAG pipelines, and multi-agent orchestration
  • 🏥 Shipped agentic AI in HIPAA-compliant healthcare environments — cut document review from 48h → 6h, reduced hallucination rates by 40%
  • ⚡ Prior background in distributed ML systems — Kafka, Spark, Airflow, anomaly detection at 1M+ records/day

📫 Open to AI Engineer roles in healthcare AI, developer tooling, or high-stakes automation where reliability actually matters.


🛠️ Tech Stack

AI / ML

LangGraph LangChain DSPy LiteLLM RAGAS LangSmith Langfuse PyTorch HuggingFace

LLM Evals · Guardrails · RAG Pipelines · Prompt Engineering · Adversarial Testing · Multi-Agent Systems

Backend / Infra

Python FastAPI Docker Kubernetes AWS Kafka Airflow

Databases

Pinecone ChromaDB PostgreSQL MongoDB Redis


Pinned Loading

  1. agentsentinel agentsentinel Public

    Agent Sentinel — Inspect, optimize, and stress-test AI agents before you ship. Static + semantic risk analysis, DSPy-powered prompt rewriting, and adversarial testing in 3 lines of code.

    Python 1 1

  2. saddle saddle Public

    Forked from rudybxn/saddle

    A self improving agent harness that diagnoses failures in a multi agent team and rewires it

    Python

  3. animind_ai animind_ai Public

    Generate and edit mathematical animations with AI — schema-driven, deterministic, and fully interactive.

    Python 1

  4. smartbag-app smartbag-app Public

    Forked from varinder1650/smartbag-app

    TypeScript 1