AI Platform Lead Engineer - Remote & Impactful

Lever, Inc.; Italia; Remoto; EUR 136.000 - 167.000; Tempo pieno

Vantaggi offerti da questo lavoro

Annual $170,000 USD cash compensation

Equity with refresh grants

Fully remote work environment

35 days PTO per year

Company retreats

Descrizione del lavoro

Lever, Inc. is seeking a Lead Engineer, AI Platform in Italy. The role blends hands-on software engineering with technical leadership to build evaluation frameworks, observability tooling, and diagnostic infrastructure for AI agents in production across models and prompts.

You will guide the AI Quality team, drive experiments, and optimize cost, latency, and user experience while collaborating with globally distributed AI teams in a highly remote and asynchronous environment.

Competenze

• 7+ years of experience building and shipping production software, ideally with LLM-powered agents.
• Experience with complex tool-using AI systems involving planning, orchestration, or sub-agents.
• Strong ability to demonstrate shipped software and how its reliability was measured.
• Excellent English communication (CEFR C2).

Mansioni

• Design, build, and own evaluation infrastructure and scoring systems for AI agents.
• Develop observability and diagnostic capabilities across planning, tool selection, and agent trajectories.
• Investigate failures and drive prototypes or prioritised improvements for AI products.
• Expand datasets via annotation, AI-generated samples, and simulated conversations to improve evaluation coverage.
• Lead and mentor the AI Quality engineering team while remaining hands-on.

Conoscenze

Leadership

LLM-powered agents

Python

Ruby on Rails

English proficiency

Strumenti

Braintrust

LangSmith

CI/CD pipelines

Descrizione del lavoro

Lever, Inc. is seeking a Lead Engineer, AI Platform in Italy. The role blends hands-on software engineering with technical leadership to build evaluation frameworks, observability tooling, and diagnostic infrastructure for AI agents in production across models and prompts.

You will guide the AI Quality team, drive experiments, and optimize cost, latency, and user experience while collaborating with globally distributed AI teams in a highly remote and asynchronous environment.