AI Model Training Engineer

Syntic AI, Inc.; United States; Remote; USD 120,000 - 180,000; Full time

Job summary

Syntic AI, Inc. seeks an experienced backend engineer to build the runtime that enables AI agents to plan, use tools, maintain memory, and recover from failures.

The role centers on orchestration and measurable improvements in agent task success without focusing on model training. You will design and implement agent orchestration, tool-calling, planning, memory management, and recovery features, while ensuring observable, interruptible, and safe agent behavior and addressing failure modes when

Qualifications

• Experience building LLM-powered applications or agents for production.
• Strong backend engineering skills in TypeScript or Python.
• Understanding of failure modes in tool-using models.

Responsibilities

• Design and implement agent orchestration and tool-calling systems.
• Support planning, memory, and recovery within the agent runtime.
• Use measurable evaluations to improve task success rates.
• Make agent behavior observable, interruptible, and safe.
• Consider failure modes that arise when models use tools.

Skills

Backend engineering

TypeScript

Python

Observability

Tools

LLM tooling

Tool-calling systems

Job description

Role overview

Build the backend runtime that enables AI agents to plan, use tools, maintain memory, and recover from failures. The role description emphasizes orchestration and measurable improvement of agent task success; it does not specify model-training methods or a particular training stack.

Responsibilities

• Design and implement agent orchestration and tool-calling systems.


• Support planning, memory, and recovery within the agent runtime.


• Use measurable evaluations to improve task success rates.


• Make agent behavior observable, interruptible, and safe.


• Consider failure modes that arise when models use tools.

Requirements

• Experience building LLM-powered applications or agents for production.


• Strong backend engineering skills in TypeScript or Python.


• Understanding of failure modes in tool-using models.