Remote AI Platform Engineer — Quality & Observability Lead

Lever, Inc.; France; À distance; EUR 128 000 - 174 000; Plein temps

Avantages offerts par ce poste

Annual equity refresh

Fully remote work

35 days PTO

Competitive benefits

Global team retreats

Résumé du poste

Lever, Inc. is seeking a Lead Engineer, AI Platform to lead the engineering foundation behind reliable AI-powered features in a fully remote role based in France. You will build evaluation frameworks, observability tooling, and diagnostic infrastructure for AI agents operating in production environments.

You’ll combine hands-on software development with technical leadership and people management, shaping the AI Quality function while collaborating with AI Core teams across time zones.

Qualifications

• 7+ years of experience building and shipping production software, ideally with LLM-powered agents.

Responsabilités

• Design, build, and own evaluation infrastructure for AI agents across tool calls and multi-turn conversations.
• Develop observability and diagnostic capabilities to identify quality issues across planning, execution, and tool use.
• Investigate failures in AI workflows and translate findings into prototypes or priorities for AI teams.
• Build datasets via human annotation, AI-generated examples, and simulated conversations to expand coverage.
• Develop experimentation frameworks for prompts, models, and agent harnesses with production baselines.
• Identify opportunities to reduce AI system cost and latency through optimization strategies.
• Set technical direction and manage day-to-day priorities for the AI Quality team while staying hands-on.
• Collaborate with AI Core teams to measure changes and improve quality.
• Establish engineering practices and evaluation approaches for reliable production AI.

Connaissances

LLM-powered agents

Technical leadership

People management

English proficiency (C2)

Outils

Ruby on Rails

Python

Braintrust

LangSmith

Description du poste

Lever, Inc. is seeking a Lead Engineer, AI Platform to lead the engineering foundation behind reliable AI-powered features in a fully remote role based in France. You will build evaluation frameworks, observability tooling, and diagnostic infrastructure for AI agents operating in production environments.

You’ll combine hands-on software development with technical leadership and people management, shaping the AI Quality function while collaborating with AI Core teams across time zones.