Senior AI Engineer — End-to-End LLM Pipelines

Crew; Bogotá ciudad; Hybrid; COP 180,000,000 - 300,000,000; Full time

Job summary

Jeeves is seeking an AI Engineer to own end-to-end AI workflows, from design to deployment. You will build production-grade LLM pipelines, manage costs and latency, and integrate AI services with Jeeves backend systems.

You will work with Product, Backend Engineering, and customers, shaping solutions with minimal hand-holding. This senior, hands-on role requires AI-native work habits, coding agents, and the ability to move fast while ensuring quality and compliance in a regulated financial

Qualifications

• 7+ years of professional software engineering experience.
• 2+ years building and operating LLM/AI-powered systems in production.
• Hands-on experience shipping LLM-powered apps with APIs like OpenAI/Anthropic.
• Experience designing agentic or multi-step AI workflows.

Responsibilities

• Own AI workflows end to end from design to iteration.
• Build production-grade LLM pipelines with prompts, outputs, validation and fallbacks.
• Integrate AI services with backend APIs, ensure data isolation and retries.
• Measure and improve AI components with logging, dashboards and alerts.
• Set patterns and tooling for reuse across the team.

Skills

Python

LLM systems

REST APIs

PostgreSQL

Cloud (AWS/GCP/Azure)

Async patterns

Observability

English fluency

Tools

OpenAI API

Anthropic

Job description

Jeeves is seeking an AI Engineer to own end-to-end AI workflows, from design to deployment. You will build production-grade LLM pipelines, manage costs and latency, and integrate AI services with Jeeves backend systems.

You will work with Product, Backend Engineering, and customers, shaping solutions with minimal hand-holding. This senior, hands-on role requires AI-native work habits, coding agents, and the ability to move fast while ensuring quality and compliance in a regulated financial