Remote AI Engineer: Production LLMs & Agent Systems

Azumo; San Francisco (CA); Hybrid; CLP 118,930,000 - 178,394,000; Full time

Benefits offered by this job

Remote first

PTO

US Holidays

AI Training

Career development

Profit sharing

US remuneration

Job summary

Azumo is hiring an AI Engineer to own production behavior of retrieval pipelines, tool-using agents, and evaluation harnesses. The role operates fully remote across Latin America, aligned to client workdays, and sits within Azumo's AI Engineer lane.

We ship production AI since 2016 and work across Azure/AWS, with a focus on reliability, measurable performance, and cost control in client environments.

Qualifications

• 4+ years building and shipping production software with Python as primary language.
• Production experience with LLM-based systems: retrieval-augmented generation and tool calling.
• Hands-on with vector/retrieval infra: pgvector, Pinecone, Qdrant, FAISS, or Azure AI Search.
• Experience with agent frameworks and tool usage in Stateful systems.
• Built evaluation suites for LLM systems with test-sets and regression tracking.
• Cloud deployment with Docker, CI/CD, and infrastructure as code.
• Clear written and spoken English (C1+).
• Bachelor's degree in CS/DS or equivalent experience.

Responsibilities

• Own production AI/ML systems behavior end-to-end.
• Develop and maintain retrieval pipelines and tool-using agents.
• Ensure reliability, performance, and cost-efficiency in live production.
• Collaborate with Data/Data Scientist/Software lanes to ship features.
• Define and implement guardrails for safe and dependable AI systems.

Skills

Python

CI/CD

Async programming

Vector databases

Retrieval systems

LangChain

English proficiency

BS in CS/DS

Education

BS in CS/DS or related field

Tools

Docker

Azure

AWS

GitHub Actions

Terraform

Job description

Azumo is hiring an AI Engineer to own production behavior of retrieval pipelines, tool-using agents, and evaluation harnesses. The role operates fully remote across Latin America, aligned to client workdays, and sits within Azumo's AI Engineer lane.

We ship production AI since 2016 and work across Azure/AWS, with a focus on reliability, measurable performance, and cost control in client environments.