AI Infrastructure / Product Engineer
ExecutivePlacements.comRemoteposted 3d ago
- PayUSD / yr
- $180k – 260k
- Where
- Remote (US)
- Posted
- Oct 14
- 3 days ago
- Type
- Full-time
- Setup
- Remote
EMPLOYMENT
Full-time
COMPENSATION
$180k - 260k/yr
ARRANGEMENT
Remote
At a glance
Build evaluation systems, backend services, and AI product features that turn legal-AI research prototypes into reliable retrieval, drafting, document, and agent workflows.
Summarized by AI from the original posting
What you'll do
- Build repeatable benchmarks for models, agents, and legal workflows
- Develop evaluation pipelines for accuracy, hallucinations, retrieval quality, latency, and cost
- Create dashboards for system performance
- Build production retrieval, drafting, document, and agent workflows
- Develop backend services, APIs, and internal tools
- Manage cloud deployments with monitoring, databases, delivery pipelines, and reliable operations
Requirements
- 01Strong Python skills
- 02Experience deploying software to the cloud
- 03Experience with APIs, databases, backend services, and deployment pipelines
- 04Interest in LLMs, retrieval-augmented generation, agents, and evaluation
- 05Ability to turn an ambiguous idea into a usable, maintainable system
- 06Full-stack experience preferred
Perks
Remote workSubstantial ownership on a distributed teamDirect access to leadership
Skills
PythonCloud DeploymentAPIsDatabasesBackend ServicesDeployment PipelinesLlmsRetrieval Augmented GenerationAi AgentsFastAPIDockerReact
Full 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.
Apply
Apply through this listing or at https://www.irys.ai/careers. Tell us about an AI system or experiment you built, how you evaluated it, and what you learned when it failed. Share only non-confidential examples.
Follow Irys, Legal AI on LinkedIn for product updates and future openings.