AI Production Reliability & Workflow Engineer

Clera; San Francisco (CA); On-site; USD 120,000 - 200,000; Full time

Benefits offered by this job

Salary range 120,000–200,000 USD

Job summary

Clera is seeking an engineer to join an early-stage AI infrastructure team in San Francisco, on-site six days a week. You will design and implement workflows that translate failure signals into actionable steps for engineering teams and build data services and user interfaces in TypeScript.

You will own the end-to-end lifecycle from detection to resolution, collaborating with customers and establishing engineering standards to improve reliability of AI agents in production.

Qualifications

• 1+ year of experience shipping production software.
• Strong full-stack TypeScript skills including frontend development and core services.
• Experience building and operating AI agents in production and understanding their failure modes.
• Experience with user-facing products, high-volume event data, data pipelines and cost-aware system design.

Responsibilities

• Turn high volumes of signals into clear, prioritized actions for engineering teams.
• Own the workflow from failure detection and alerting through triage and resolution.
• Connect product workflows with collaboration, issue-tracking, code-hosting, and coding-agent tools.
• Design how people and AI agents work together to investigate and fix issues.
• Build across the full stack in TypeScript, including data services and user-facing interfaces.
• Work directly with customers and help establish engineering standards.

Skills

Full-stack TypeScript

Frontend development

Core services

Production software

Job description

Clera is seeking an engineer to join an early-stage AI infrastructure team in San Francisco, on-site six days a week. You will design and implement workflows that translate failure signals into actionable steps for engineering teams and build data services and user interfaces in TypeScript.

You will own the end-to-end lifecycle from detection to resolution, collaborating with customers and establishing engineering standards to improve reliability of AI agents in production.