AI Infrastructure / Product Engineer

Irys, Legal AI; United States; On-site; USD 180,000 - 260,000; Full time

Job summary

Irys, Legal AI seeks an AI Infrastructure / Product Engineer to build evaluations, services, and product features that advance applied AI in legal work.

This full-time, remote role within the United States offers significant ownership on a distributed team, with direct access to leadership to shape measurement and quality improvements.

You will work on benchmarks, evaluation pipelines, dashboards, and production features across retrieval, drafting, document, and agent workflows.

Qualifications

• Strong Python skills and cloud deployment experience.
• Experience with APIs, databases, backend services, and deployment pipelines.
• Interest in LLMs, retrieval-augmented generation, and evaluation.

Responsibilities

• Build repeatable benchmarks for models, agents, and legal workflows.
• Develop evaluation pipelines for accuracy, hallucinations, retrieval quality, latency, and cost.
• Create dashboards to visualize system performance changes.
• Develop production features turning research prototypes into usable retrieval, drafting, document, and agent workflows.
• Implement backend services, APIs, and internal tools for testing and releasing improvements.
• Manage cloud deployments with monitoring and CI/CD pipelines.

Skills

Python

Cloud deployment

APIs & databases

Backend services

Deployment pipelines

LLMs / RAG

Full-stack experience

FastAPI

Docker

React/Next.js

Postgres

Vector databases

Tools

FastAPI

Docker

React/Next.js

Postgres

Vector databases

Job description

Help promising AI experiments become dependable products.

Irys is hiring an AI Infrastructure / Product Engineer to build the evaluations, services, and product features that bring applied AI into legal work.

Full-time · Remote · United States only

Annual base salary: $180,000-$260,000 USD. Final base salary within this range depends on relevant skills, experience, and role scope.

What you will build

• Repeatable benchmarks for models, agents, and legal workflows.
• Evaluation pipelines covering accuracy, hallucinations, retrieval quality, latency, and cost.
• Dashboards that make changes in system performance visible.
• Production features that turn research prototypes into usable retrieval, drafting, document, and agent workflows.
• Backend services, APIs, and internal tools that help the team test and release improvements.
• Cloud deployments with monitoring, databases, delivery pipelines, and reliable operations.

What you bring

• Strong Python skills and experience deploying software to the cloud.
• Confidence working with APIs, databases, backend services, and deployment pipelines.
• An interest in LLMs, retrieval-augmented generation, agents, and evaluation.
• The ability to turn an ambiguous idea into a usable, maintainable system.

Full-stack experience is preferred. Experience with FastAPI, Docker, React/Next.js, Postgres, vector databases, AI benchmarks, or document automation would be helpful.

Why Irys

You will work close to AI research while staying connected to the product and its users. The role offers substantial ownership on a distributed team, with direct access to leadership and the opportunity to influence how we measure and improve quality.

Irys was founded by lawyers and AI researchers. We build tools that help legal professionals complete work they can inspect, refine, and stand behind.

Follow Irys, Legal AI on LinkedIn for product updates and future openings.