Skip to content

Mehdi Salhi

AI/ML Engineer &
Cloud Architect

Building custom AI systems on AWS. RAG pipelines, AI agents, and production ML infrastructure. Based in Stamford, CT / NYC.

Unkommon.ai

Founder

AWS

Cloud Platform

3.71

GPA @ SNHU

About

I build custom AI systems on AWS. RAG pipelines that let teams search thousands of documents in seconds, AI agents that automate multi-step workflows, and the production infrastructure to run it all reliably. Most of my work sits at the intersection of machine learning engineering and cloud architecture.

I founded Unkommon.ai to solve a problem I kept seeing: companies spending months on AI projects that never make it to production. The model works in a notebook but breaks on real data. The chatbot demo impresses leadership but can't handle actual customer questions. Unkommon builds the systems that actually ship. On your infrastructure, with your data, in weeks.

On the side I'm wrapping up my Computer Science degree at Southern New Hampshire University, graduating July 2026 with a 3.71 GPA. School has been good but honestly building things has taught me more.

3.71

Dean's List

GPA

Southern New Hampshire University

Jul 2026

Graduating

Computer Science, B.S.

CT / NYC

Location

Stamford, Connecticut

AI + Cloud

Focus

AWS, LLMs, Agentic Systems

Currently buildingActive

Unkommon.ai

Custom AI/ML engineering studio. We build production-grade RAG systems, AI agents, ML integrations, and cloud infrastructure for companies with complex problems. AWS-native. HIPAA-compliant architecture.

RAG SystemsAI AgentsAWSLangGraph
unkommon.ai

Skills

Technologies I work with

AWS & Cloud

LambdaDynamoDBAPI GatewayEC2S3SageMakerBedrockServerlessCloudFormationTerraform

AI / ML

RAG PipelinesLLM OrchestrationAgentic SystemsVector DatabasesPrompt EngineeringFine-TuningLangGraphClaude CodeCursor

Software

PythonJavaScriptTypeScriptNode.jsReact / Next.jsReact NativeSwiftFastAPI

Projects

Selected work and coursework

Featured

Unkommon.ai

Custom AI/ML engineering platform. RAG systems, multi-agent architectures, ML consulting, and production cloud infrastructure. Built with React, TypeScript, Express, deployed on AWS.

ReactTypeScriptAWSPython
Live Demo

Company Policy RAG System

Production-grade RAG system with hybrid search, cross-encoder reranking, and RAGAS evaluation metrics. Upload any document and ask questions in natural language. Built with Python, LangChain, FastAPI, deployed on Hugging Face.

PythonLangChainFastAPIChromaDB

MuscleMeal AI

iOS app that generates personalized meal recipes using Gemini AI, tailored to fitness goals and dietary preferences.

SwiftSwiftUICore DataGemini API