Rogo
Software Engineer: Internal Automation
About this role
Join Rogo's Internal Automation team to build backend systems that automate internal workflows and integrate disparate enterprise systems using AI agents. You'll own production services spanning data pipelines, customer lifecycle automation, and LLM-powered agents while working with the same technology that powers Rogo's core financial AI platform.
What you'll do
- Design and deploy end-to-end production backend services for internal operations, from ambiguous problems to monitored systems
- Build data integration layer connecting CRM, billing, product usage, and other systems into unified queryable records
- Develop and operationalize AI agent workflows that run unattended with proper evals, guardrails, and monitoring
- Create provisioning and onboarding systems for enterprise customer setup and implementation
- Instrument systems to measure impact (hours saved, error rates, cycle time) and retire underperforming automations
- Integrate third-party APIs securely while handling sensitive company and customer data
What they're looking for
- TypeScript backend development
- Production cloud deployment (GCP preferred)
- Relational databases and SQL schema design
- LLM application development (prompting, function calling, agents)
- Third-party API integration and data reconciliation
- Asynchronous patterns (queuing, background jobs, retries)
- Observability and monitoring (logging, metrics, tracing)
- Stakeholder communication and requirements translation
Opens the application — the Jobs AI extension fills it for you. Set up autofill
Opens the official application on the employer’s site. No login required.
Rogo
Rogo builds a financial AI platform with a focus on data-driven insights and user experience. The company is hiring Analytics Engineers to develop data pipelines and reporting tools, and Design Engineers to enhance its design system and user interactions.
View all jobs at RogoLikely interview questions
- Describe a production backend system you shipped end-to-end—what was the most complex operational problem you solved?
- Walk us through how you've built and evaluated an LLM agent workflow in production; what guardrails did you implement?