Senior AI Engineer - Backend LLM Lead (Remote, Flexible)

BairesDev; Nuevo León; Presencial; MXN 2.036.000 - 3.053.000; Jornada completa

Ventajas ofrecidas por este puesto de trabajo

100% remote

USD compensation or local currency

Hardware provided

Flexible hours

Parental leave

Global team mentorship & growth

Descripción de la vacante

BairesDev is seeking a Staff AI Engineer to lead backend AI features end to end, collaborating with a Principal Engineer and a tech lead. You will remain hands-on while guiding the team, shaping LangGraph flows, RAG pipelines, and production LLM systems.

You will own evaluation coverage, unblock engineers, and contribute to scalable AI infrastructure across distributed services, REST/GraphQL on AWS, and CI/CD pipelines.

Formación

• 8+ years of experience in Python.
• Proven experience building, maintaining, and evolving production LLM systems.
• Hands-on with LangChain and LangGraph, including agent flows and state management.
• Experience with RAG pipelines over structured and unstructured data.
• Experience with LLM evaluation and tracing (LangSmith, LLM-as-judge, golden datasets).
• 4+ years of React/Next.js and TypeScript experience.
• Strong prompt engineering and routine exposure to CI/CD and observability.

Responsabilidades

• Lead and own backend AI features end to end, delivering complex work.
• Build and maintain LangGraph agent flows and RAG pipelines across data types.
• Hold evaluation and tracing coverage on shipped AI behavior.
• Stay hands-on across development phases, collaborating with Principal and Senior engineers.
• Unblock Senior engineers in the pod and surface blockers early.

Conocimientos

Python

English (Advanced)

LLM systems design

Distributed systems

Prompt engineering

Team leadership

CI/CD practices

Herramientas

LangChain

LangGraph

React/Next.js

TypeScript

AWS

REST/GraphQL

Pinecone

Descripción del empleo

BairesDev is seeking a Staff AI Engineer to lead backend AI features end to end, collaborating with a Principal Engineer and a tech lead. You will remain hands-on while guiding the team, shaping LangGraph flows, RAG pipelines, and production LLM systems.

You will own evaluation coverage, unblock engineers, and contribute to scalable AI infrastructure across distributed services, REST/GraphQL on AWS, and CI/CD pipelines.