Skip to content
View samit9495's full-sized avatar
1 follower · 0 following

Achievements

Achievement: Pull Sharkx2Achievement: YOLO

Achievements

Achievement: Pull Sharkx2Achievement: YOLO

Block or report samit9495

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
samit9495/README.md

Hi, I'm Samit Pawar

AI engineer with 8 years of production Python. I build with large language models — agents, RAG, and agentic workflows that ship to production behind tests and guardrails — not just call APIs.

Day to day I'm a senior engineer on a regulated, multi-tenant healthcare SaaS, where I deliver ~35 production tickets/month via AI-pair, test-driven development. On the side I build full-stack AI systems end-to-end to push the same ideas further.

What I work on

  • LLM agents & orchestration — tool use, planning, multi-step reasoning with LangChain / LangGraph
  • Retrieval-Augmented Generation (RAG) — hybrid retrieval over domain corpora and project memory
  • AI reliability — evaluation frameworks, prompt-audit logging, behavioral/security guardrails
  • Model Context Protocol (MCP) — agents that act on live schema/log/ticket state, not hallucinated context
  • Production engineering — FastAPI / Django, PostgreSQL, AWS, React/TypeScript, CI/CD, TDD

Featured builds

Agentic SRE Observability Platform — Repo End-to-end agentic observability: anomaly detection → incident correlation → 4-agent Gemini triage (RAG over runbooks) → React dashboard. Driven test-first to 98.75% coverage / 246 tests behind a 5-job CI gate. Python · FastAPI · Gemini · React · TypeScript · Docker

HR Compensation Analytics Platform — Repo Full-stack comp-analytics for a 10,000-employee org: compa-ratio / range-penetration / percentile analytics via SQL window functions, with an AI-assisted React dashboard. 99% test coverage; deployed to Fly.io + Vercel. Python · FastAPI · SQLAlchemy · React · TanStack · Recharts

GitaFlow — Autonomous AI Content Engine — Repo A 7-stage multi-LLM pipeline that turns each of 701 Bhagavad Gita verses into video: RAG-grounded scripts, local voice-clone TTS, local diffusion art, and Whisper captions on a swappable model layer. Python · Gemini/Claude/GPT · LlamaIndex + ChromaDB · local ML

Tech I reach for

Python TypeScript SQL · LangChain LangGraph LlamaIndex · RAG MCP OpenAI/Anthropic/Gemini APIs · FastAPI Django · React Tailwind · PostgreSQL Redis · AWS (Lambda/ECS/CloudFormation) Docker GitHub Actions · pytest TDD

Elsewhere

AWS Certified Developer – Associate · Based in Noida, India · open to remote AI/engineering roles.

Pinned Loading

  1. agentic-observability-platform agentic-observability-platform Public

    Agentic SRE observability platform: log ingestion -> anomaly detection -> incident correlation -> Gemini multi-agent triage (RAG over runbooks) -> React dashboard. Runs offline; test-first.

    Python

  2. hr-compensation-analytics hr-compensation-analytics Public

    Full-stack salary/compensation analytics for 10k employees (compa-ratio, range penetration, percentile outliers) - FastAPI + React, TDD at 99% coverage.

    TypeScript

  3. GitaFlow GitaFlow Public

    Autonomous AI content engine: a 7-stage multi-LLM pipeline (RAG + local Whisper/TTS/diffusion) that turns text into narrated video.

    Python

  4. Labelbymahi Labelbymahi Public

    Production Django e-commerce platform with live Razorpay payments and a custom coupon engine, deployed on AWS EC2 / Oracle Cloud.

    Python

  5. samit-portfolio samit-portfolio Public

    Developer portfolio site - React + TypeScript, deployed on Cloudflare Pages.

    TypeScript

  6. Atbasher Atbasher Public

    Multi-threaded Atbash cipher CLI that encrypts multiple text files in parallel (one thread per CPU).

    Python