CM

Open to opportunities

Carlos Medina

@carlosmedina1

AI backend engineer building production LLM and RAG features with scalable, low-latency services.

What I'm looking for

I’m looking to build and ship production LLM/RAG backends—microservices, vector search, and agent workflows—where I can improve retrieval, reduce latency, and turn business needs into reliable AI products on scalable cloud infrastructure.

I’m an AI Backend Engineer with 8+ years building backend systems and AI-powered applications using LLMs, RAG pipelines, and scalable cloud architectures. I focus on delivering production-grade AI features such as copilots, intelligent search, and agent-based workflows.

I’ve built and deployed 6+ LLM-powered features using OpenAI and Anthropic APIs, including chat assistants and internal copilots. I designed RAG pipelines for enterprise knowledge bases, improving retrieval accuracy by 42%, and developed backend microservices in Python (FastAPI) and TypeScript (Node.js) for high-throughput AI workloads.

I also integrate vector databases like Pinecone and Weaviate for semantic search across millions of documents, and I collaborate on multi-step reasoning with LangChain and LangGraph. Across roles, I’ve optimized prompt engineering to reduce response latency by 30% and improved user-facing outcomes—while continuously experimenting with emerging LLM technology to enhance performance and user experience.

Experience

Work history, roles, and key accomplishments

GL

AI Backend Engineer

Jan 2024 - Mar 2026 (2 years 2 months)

Built and deployed 6+ LLM-powered features (chat assistants and internal copilots) using OpenAI and Anthropic APIs. Designed RAG pipelines that improved enterprise knowledge retrieval accuracy by 42% and optimized prompt engineering to reduce response latency by 30%.

Python fastAPI TypeScript LLM RAG LangGraph Pinecone Weaviate

SS

Backend Engineer

Simbo Sonora

Jan 2020 - Dec 2023 (3 years 11 months)

Developed AI-assisted messaging and workflow orchestration using LLM APIs, including REST backend services for multi-tenant architectures. Implemented document ingestion and embedding pipelines for semantic search and integrated LLM-based classifications that reduced manual processing by 35%.

Python REST APIs SQL PostgreSQL Embeddings Semantic Search

CO

Full Stack Developer

Coderio

Jan 2019 - Dec 2019 (11 months)

Built full-stack web applications using React, Node.js, and Python backend services, including modular APIs for third-party integrations and data-heavy workflows. Implemented early semantic search prototypes with embeddings and contributed to system design improvements that reduced API response times by 25%, using AWS and Dockerized deployments.

React Node Python REST APIs GraphQL Embeddings Semantic Search AWS Docker

Education

Degrees, certifications, and relevant coursework

PM

Polytechnic University of the State of Morelos

Bachelor's Degree, Computer Science

2015 - 2019

Completed a Bachelor's degree in Computer Science at the Polytechnic University of the State of Morelos from 2015 to 2019.

Tech stack

Software and tools used professionally

PostgreSQL

Gmail

Node.js

Redis

JavaScript

FastAPI

GraphQL

SQL

LangChain

Weaviate

Pinecone

LangGraph

Availability

Open to opportunities

Location

Mexico

Authorized to work in

Website

carlosamedina.in

Job categories

AI Backend Engineer AI Engineer Backend Engineer Full Stack Developer LLM Engineer Senior AI Backend Developer Senior Backend Developer (Artificial Intelligence)Senior Machine Learning Backend Engineer

Interested in hiring Carlos?

You can contact Carlos and 90k+ other talented remote workers on Himalayas.

People also viewed

View all talent

Find your dream job

Sign up now and join over 250,000+ remote workers who receive personalized job alerts, curated job matches, and more for free!