Remote Senior AI Engineer - Multi-Agent Platform Leader

BairesDev; Colombia; A distancia; COP 279.520.000 - 403.752.000; Jornada completa

Ventajas ofrecidas por este puesto de trabajo

100% remote work

Descripción de la vacante

BairesDev is seeking a Senior AI Engineer to contribute to the architecture of an enterprise AI assistant used across multiple functions. You will stay hands-on in code, shaping orchestration design, retrieval strategies, and evaluation approaches for a scalable AI platform.

You will work with distributed teams, design multi-agent workflows, and implement robust evaluation methods while progressing on high-impact enterprise projects.

Formación

• Experience in Python required.
• Background working on agentic or LLM platforms in production.
• Familiarity with LangChain and LangGraph, including multi-agent orchestration and tool invocation.
• Experience with LLM evaluation strategy, including offline evals or golden dataset design.
• Experience with RAG over structured and unstructured sources.
• Experience with React and TypeScript.
• Experience with distributed systems and REST/GraphQL on AWS.
• Advanced level of English.

Responsabilidades

• Contribute to architecture decisions for an enterprise-scale agentic AI platform.
• Help design multi-agent orchestration, including skill invocation and routing.
• Support retrieval strategy across structured and unstructured data sources.
• Help build and evolve the evaluation harness used to validate AI system behavior.
• Collaborate with distributed engineering teams and support technical decisions.

Conocimientos

Python

Agentic/LLM platforms

LangChain

LangGraph

LLM evaluation

RAG

React

TypeScript

AWS

REST/GraphQL

English (advanced)

Herramientas

React

TypeScript

AWS

REST/GraphQL

Descripción del empleo

BairesDev is seeking a Senior AI Engineer to contribute to the architecture of an enterprise AI assistant used across multiple functions. You will stay hands-on in code, shaping orchestration design, retrieval strategies, and evaluation approaches for a scalable AI platform.

You will work with distributed teams, design multi-agent workflows, and implement robust evaluation methods while progressing on high-impact enterprise projects.