Skip to content
View satyamsh04's full-sized avatar
  • Sydney, New South Wales, Australia

Block or report satyamsh04

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
satyamsh04/README.md

Satyam Sharma

AI engineering graduate building multi-agent systems, LLM evaluation pipelines, and production AI tooling. Based in Gold Coast, Australia — open to graduate AI/ML engineering roles in 2026.


What I Build

  • Multi-agent AI systems — autonomous pipelines with role-separated agents (Researcher, Analyst, Writer, Critic) using LangChain and OpenAI
  • LLM evaluation & reliability — automated scoring pipelines to benchmark agent accuracy, latency, and failure modes
  • Production MCP servers — Model Context Protocol servers integrating AWS S3, DynamoDB, Slack, and JWT auth for real-world data annotation workflows

Tech Stack

Python TypeScript Node.js React

AI/ML: OpenAI API · LangChain · Streamlit · MCP Protocol · Ollama

Cloud/Infra: AWS S3 · DynamoDB · Vercel

Tools: Git · VS Code · Cursor IDE · Docker


Featured Projects

Project Description Stack
ai-email-assistant Multi-agent email triage, draft & reply pipeline — WIL industry project Python · OpenAI · LangChain
agent-eval-pipeline Automated evaluation & reliability scoring for LLM agents TypeScript · OpenAI
multi-agent-research-assistant 4-agent research report pipeline with Critic revision loop & Streamlit UI Python · LangChain · Streamlit
custom-mcp-server Production MCP server — S3, DynamoDB, Slack, JWT auth TypeScript · AWS · MCP

Education

Bachelor of Computer Science (Data Science focus) — Griffith University · GPA 5.1 · Graduating June 2026


Contact


GitHub Stats

Pinned Loading

  1. agent-eval-pipeline agent-eval-pipeline Public

    Automated evaluation and reliability scoring pipeline for LLM-based agents (TypeScript)

    TypeScript

  2. custom-mcp-server custom-mcp-server Public

    Production MCP server for data annotation workflow (S3, DynamoDB, Slack, JWT auth)

    TypeScript

  3. multi-agent-research-assistant multi-agent-research-assistant Public

    Four-agent (Researcher to Analyst to Writer to Critic) research-report pipeline with a Critic-driven revision loop, Serper live search, OpenClaw/OpenAI backends, and a Streamlit UI.

    Python

  4. iammimii/AI-Agent-Concept-Workshop-Academic-Automation iammimii/AI-Agent-Concept-Workshop-Academic-Automation Public

    JavaScript 1

  5. mern-social-media-app mern-social-media-app Public

    Full-stack social media app — MongoDB, Express, React, Node.js (MERN stack)

    JavaScript

  6. network-analysis-notebooks network-analysis-notebooks Public

    Network analysis and graph algorithms using Python and NetworkX — Griffith University

    Jupyter Notebook