Remote ML Platform Engineer - AI Infra & LLMs

BairesDev; Bogotá; Remote; COP 324,496,000 - 454,295,000; Full time

Benefits offered by this job

100% remote work

Competitive USD compensation

Home office setup provided

Flexible schedule

Parental leave & holidays

Mentorship & growth opportunities

Multicultural, top 1% global talent

Job summary

Join BairesDev, a global tech leader, as an ML Platform Engineer (AI) working 100% remotely. You’ll build and maintain internal AI infra, connect ML research with production engineering, and ensure robust model gateways and evaluation pipelines.

Collaborate across teams to standardize end-to-end ML workflows and security. You’ll deploy scalable LLM serving, optimize vector stores, and implement comprehensive observability.

Qualifications

• 4+ years in ML Platform Engineering, DevOps, or Infrastructure Engineering.
• Proven experience with internal AI infrastructure and model gateways.
• Strong Kubernetes and Docker expertise.
• Hands-on with LLM serving frameworks like vLLM or TGI and cloud AI services.

Responsibilities

• Architect and manage production-grade internal AI infra including model gateways and deployment platforms.
• Design automated evaluation pipelines to ensure quality of LLM outputs.
• Build scalable vector stores for retrieval-augmented generation and data retrieval.
• Deploy and manage high-performance LLM serving solutions (vLLM/TGI).
• Implement observability and monitoring for model performance and system health.
• Collaborate with apps teams to standardize workflows for training, inference, and security.

Skills

ML Platform Eng

Kubernetes

Docker

vLLM/TGI

AWS Bedrock/Azure OpenAI

Python

English

Job description

Join BairesDev, a global tech leader, as an ML Platform Engineer (AI) working 100% remotely. You’ll build and maintain internal AI infra, connect ML research with production engineering, and ensure robust model gateways and evaluation pipelines.

Collaborate across teams to standardize end-to-end ML workflows and security. You’ll deploy scalable LLM serving, optimize vector stores, and implement comprehensive observability.