Skip to content
View samarth70's full-sized avatar
5 followers · 30 following

Achievements

Achievement: Pair ExtraordinaireAchievement: Pull Shark

Achievements

Achievement: Pair ExtraordinaireAchievement: Pull Shark

Block or report samarth70

Report abuse

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

Report abuse
samarth70/README.md

Hi, I'm Sam Agarwal 👋

AI Software Engineer — production LLM systems, multi-agent architectures & edge-native AI
MS Data Science @ Stony Brook University · ex-Genpact (2.5+ yrs) · ex-ARMA AI Labs, CA, US

🔭 What I build

I turn LLMs into reliable, cheap, production systems : RAG pipelines, agentic workflows, LoRA fine-tuning, and evaluation harnesses that make model behavior measurable. Recently focused on edge-native AI (Cloudflare Workers, Pyodide/WASM) that runs fast and costs near-zero.

🚀 Featured projects

Project What it does Stack
ParamMem Parametric reflective memory for LLM agents: cut agent reflection latency 94% (45s→2.8s), +11.4% HumanEval LoRA · Llama-3 · Groq · ChromaDB · FastAPI · React
PrepGenie Edge-native AI interview coach + resume reviewer; recursive LLM failover, LLM-as-Judge scoring Pyodide/WASM · Gemini→Groq→Mistral · Gradio
AI Pentest Scanner Autonomous multi-agent security scanner: recon → vuln detection → auto-report Multi-agent · Groq/Gemini · Nmap/Shodan · React/Flask
Real-Time Stocks (Serverless) Global stock dashboard on the edge; pull-on-demand caching → 1 API call/min/symbol at scale Cloudflare Workers · D1 · R2 · Vite

🤗 Also on Hugging Face — 15+ live Spaces including Neural Style Transfer (62 ❤️), plus PrepGenie, the AI Pentest API, and the ParamMem reasoning dashboard.

🌱 Open source

I contribute fixes to the backend and developer tooling I use day to day. A few of the most significant ones are in Supabase (auth & storage), Grafana (k6), Cloudflare (workers-sdk), Zendesk (maxwell) and Sourcegraph (go-diff), plus ongoing work across agent-evaluation and MCP projects.

🛠️ Tech

AI/LLM: PyTorch · TensorFlow · LangChain · RAG · LoRA · MCP · DeepEval · Agentic Workflows · LLM-as-Judge Backend: Python · Java/Spring Boot · C++ · FastAPI · Flask · REST · SQL Data & Infra: ChromaDB · Pinecone · Pandas · Spark · AWS · Cloudflare · Docker · Git

💼 Experience

  • Generative AI Engineer Intern — ARMA AI Labs (2025): built a DeepEval-based eval framework (7 metrics) + a production model-routing pipeline.
  • Senior Associate Software Developer — Genpact (2022–2024): shipped Salesforce/Spring Boot systems for High Profile Clients; cut manual data entry 60%.

Open to AI/ML Software Engineer roles · Always happy to collaborate on LLM & agent projects.

Pinned Loading

  1. AI-Pentest-Scanner AI-Pentest-Scanner Public

    Autonomous multi-agent AI penetration-testing tool — recon, vulnerability detection and auto-reporting via Groq/Gemini agents with Nmap/Shodan. React + Flask + Cloudflare.

    Python 1

  2. E-Election-Assist-Project/Manifesto-Explainer E-Election-Assist-Project/Manifesto-Explainer Public

    Analyzing Political Parties Manifesto With Text Mining. Part Of My B.Tech Final Year Project.

    Python 1

  3. ParamMem ParamMem Public

    Parametric reflective memory for LLM agents — a LoRA-tuned memory module that cuts agent reflection latency 94% (Llama-3, Groq, ChromaDB, FastAPI + React dashboard).

    Python 1

  4. Prepgenie-Mock-Interview-system Prepgenie-Mock-Interview-system Public

    Edge-native AI mock-interview coach and resume reviewer — Pyodide/WASM, recursive LLM failover (Gemini→Groq→Mistral) and LLM-as-Judge scoring.

    Python 1

  5. Political-Party-Symbol-Detector Political-Party-Symbol-Detector Public

    Custom YOLOv5 detector for political party symbols, with a deployed inference API.

    Python 2

  6. real-time-stocks-serverless real-time-stocks-serverless Public

    Real-time stock dashboard on the Cloudflare edge (Workers + D1 + R2) with pull-on-demand caching — one upstream API call per minute per symbol at scale.

    JavaScript 1