Remote AI Infrastructure Engineer — LLM Serving & Cloud AI

BairesDev; Chile; Remote; CLP 119,284,000 - 188,867,000; Full time

Benefits offered by this job

100% remote work

Excellent USD compensation

Hardware and software setup for home

Flexible hours

Parental leave and vacations

Multicultural global team

Job summary

BairesDev is seeking an AI Infrastructure Engineer to design and scale internal AI infrastructure, enabling model serving, agent deployment, and AI workloads across distributed teams.

You will build production-ready environments with Kubernetes and Docker, integrate AWS Bedrock or Azure OpenAI, and establish observability with Langfuse/LangSmith. Strong English required and 4+ years in AI infra.

Qualifications

• 4+ years of experience in AI Infrastructure, DevOps, or Platform Engineering.
• Experience building internal AI infrastructure including model gateways and eval pipelines.
• Proficiency in Python and containerization (Kubernetes, Docker).
• Hands-on experience with LLM serving frameworks such as vLLM or TGI and cloud AI services like AWS Bedrock or Azure OpenAI.
• Observability/evaluation tools like Langfuse or LangSmith are a plus.
• Advanced English proficiency.

Responsibilities

• Architect and maintain internal AI infrastructure, including model gateways and agent deployment platforms.
• Implement and optimize LLM serving solutions using technologies like vLLM and TGI.
• Design and manage scalable vector stores and evaluation pipelines to support AI-driven applications.
• Build and maintain production-grade containerized environments using Kubernetes and Docker.
• Integrate cloud-based AI services such as AWS Bedrock or Azure OpenAI into the core infrastructure.
• Implement comprehensive observability for AI workflows using Langfuse and LangSmith.

Skills

Python

Kubernetes

Docker

vLLM

TGI

Langfuse

LangSmith

English

AI Infra 4+ yrs

Tools

Kubernetes

Docker

vLLM

TGI

AWS Bedrock

Azure OpenAI

Job description

BairesDev is seeking an AI Infrastructure Engineer to design and scale internal AI infrastructure, enabling model serving, agent deployment, and AI workloads across distributed teams.

You will build production-ready environments with Kubernetes and Docker, integrate AWS Bedrock or Azure OpenAI, and establish observability with Langfuse/LangSmith. Strong English required and 4+ years in AI infra.