AI Platform Engineer - Production LLM & RAG Systems

present of AI; San Francisco (CA); Presencial; USD 180 000 - 240 000; Tempo integral

Resumo da oferta

Readily is building the shared AI foundation that engineers use to ship language model features quickly and safely. The role covers retrieval, prompting, evaluation and model routing in a regulated healthcare context, where outputs must be defensible and traceable.

You will ship production LM systems using Python and TypeScript, reinforce solid backend basics, document clearly, and help unblock colleagues through thoughtful tooling and monitoring.

Qualificações

• This role requires shipping LM systems in production and a habit of measuring quality.
• Candidate writes clean Python and TypeScript.
• Strong backend fundamentals and documentation to unblock teammates.

Responsabilidades

• Build the shared AI foundation used by engineers for retrieval, prompting, evaluation and routing.
• Ensure model outputs are traceable and defensible under regulated requirements.
• Develop evaluation harnesses and monitoring to keep quality steady.
• Operate a model gateway with routing and cost tracking.

Conhecimentos

Python

TypeScript

Retrieval

RAG

Agents

Evaluation

Monitoring

Backend

Documentation

Cloud basics

Ferramentas

Git

CI/CD

AWS

Docker

Descrição da oferta de emprego

Readily is building the shared AI foundation that engineers use to ship language model features quickly and safely. The role covers retrieval, prompting, evaluation and model routing in a regulated healthcare context, where outputs must be defensible and traceable.

You will ship production LM systems using Python and TypeScript, reinforce solid backend basics, document clearly, and help unblock colleagues through thoughtful tooling and monitoring.