Remote Lead Engineer – AI Quality Platform

CIRCLE; Madrid; A distancia; EUR 120.000 - 180.000; Jornada completa

Ventajas ofrecidas por este puesto de trabajo

Equity in company

35 days paid time off

Remote-only team

Company retreats

Descripción de la vacante

Circle, a remote-only company building an AI-powered platform, seeks a Lead Engineer for the AI Quality engineering team. You will own evaluation infrastructure, build observability tooling, and guide a growing team while staying hands-on in code.

You'll diagnose quality across the agent pipeline, design datasets, run experiments across prompts and models, and collaborate with AI Core engineering to improve product quality at scale in a fast-paced, global environment.

Formación

• 7+ years of experience building and shipping production software.
• Experience with LLM-powered agents and multi-tool architectures is a plus.
• Proficiency in Ruby on Rails and Python; ability to learn quickly.
• Experience building eval pipelines, observability, and dashboards.
• Ability to design datasets and annotation workflows for ML/AI evaluation.
• Fast learner, adaptable, and comfortable in a dynamic environment.
• Strong alignment with company values and fluent English.

Responsabilidades

• Build and own evaluation infrastructure, CI/CD pipelines, scorers, and datasets for AI agents.
• Diagnose quality issues across the agent pipeline and prioritize fixes.
• Grow datasets with annotations, AI-generated and simulated conversations.
• Run structured experiments across prompts, models, and agent harness.
• Lead and grow the AI Quality engineering team while staying hands-on.
• Partner with AI Core engineering to ensure changes improve quality.

Conocimientos

Production software engineering

Experimentation at scale

Team leadership

English proficient

Strong communication

Herramientas

Ruby on Rails

Python

Braintrust

LangSmith

CI/CD tooling

Descripción del empleo

Circle, a remote-only company building an AI-powered platform, seeks a Lead Engineer for the AI Quality engineering team. You will own evaluation infrastructure, build observability tooling, and guide a growing team while staying hands-on in code.

You'll diagnose quality across the agent pipeline, design datasets, run experiments across prompts and models, and collaborate with AI Core engineering to improve product quality at scale in a fast-paced, global environment.