AI Agent Platform Engineer — Automation & Safety

TikTok USDS Joint Venture; San Jose (CA); On-site; USD 137,000 - 360,000; Full time

Job summary

TikTok USDS Joint Venture LLC seeks a software engineer to design the Agentic Service Bot and multi-agent orchestration systems for a scalable safety platform within the USDS environment.

You will develop core components such as agent runtime, state management, and tool-calling frameworks, build modern UIs, and collaborate with Data Science to integrate LLMs into production workflows with low latency and high reliability.

Qualifications

• Bachelor's or Master's degree in Computer Science or a related field.
• 3+ years of professional software engineering experience building large-scale production systems.
• Strong backend experience in Go, Java, or Python with distributed systems knowledge.
• Hands-on experience with modern web technologies (TypeScript, React) to build internal tools.
• Experience integrating LLM/ML capabilities into products.

Responsibilities

• Design and build core platform components including agent runtime, state management, and tool-calling frameworks to enable multi-agent coordination.
• Build modern UIs and workflow editors to monitor, debug, and configure AI workflows.
• Partner with Data Science to integrate LLMs and detection models into reusable workflow nodes with high reliability and low latency.
• Drive migration of critical data pipelines to USDS and ensure 100% recovery for safety-critical services.
• Collaborate with product to translate safety needs into scalable engineering solutions.

Skills

Go/Java/Python

Distributed systems

TypeScript/React

LLM/ML integration

0→1 builder

Education

Bachelor's or Master's in Computer Science or related field

Tools

Temporal

Airflow

React Flow

Job description

TikTok USDS Joint Venture LLC seeks a software engineer to design the Agentic Service Bot and multi-agent orchestration systems for a scalable safety platform within the USDS environment.

You will develop core components such as agent runtime, state management, and tool-calling frameworks, build modern UIs, and collaborate with Data Science to integrate LLMs into production workflows with low latency and high reliability.