Workflow Automation Engineer

Syntic AI, Inc.; United States; Remote; USD 110,000 - 160,000; Full time

Job summary

Syntic AI, Inc. is seeking an experienced backend engineer to design and build backend systems for automating AI-powered workflows. You will work on orchestration, planning, memory, and recovery to improve reliability and controllability of agent behavior.

The role focuses on developing robust runtimes, tool integration, and observability, with emphasis on safety in model-tool interactions. Collaborate with product and research teams to push AI-enabled automation forward.

Qualifications

• Experience building LLM-powered applications or agents for production use.
• Strong backend engineering skills in TypeScript or Python.
• Understanding of failure patterns in models that interact with tools.

Responsibilities

• Design and implement agent orchestration and tool-calling systems.
• Build runtime features that support planning, memory and recovery.
• Use measurable evaluations to identify ways to increase task success.
• Make agent behavior observable and interruptible.
• Improve safety by addressing failure modes in tool-using models.

Skills

LLM-powered applications

Backend engineering

Tools

TypeScript

Python

Job description

Role overview

Create backend systems for automating workflows with AI agents, supporting their planning, tool use, memory and recovery. The work includes building orchestration capabilities and improving the reliability and controllability of agent behavior through evaluation and observability.

Responsibilities

• Design and implement agent orchestration and tool-calling systems.
• Build runtime features that support planning, memory and recovery.
• Use measurable evaluations to identify ways to increase task success.
• Make agent behavior observable and interruptible.
• Improve safety by addressing failure modes in tool-using models.

Requirements

• Experience building LLM-powered applications or agents for production use.
• Strong backend engineering skills in TypeScript or Python.
• Understanding of failure patterns in models that interact with tools.