CareerPlanSign in

大模型Multi-Agent Harness工程师 - Seed Model

北京💼 Full-time🗓 2026-09-28

Core

Develop Long-Running Multi-Agent Harness and build infrastructure for Multi-Agent Reinforcement Learning (RL) agents.

Role type

Senior IC Machine Learning Engineer (Multi-Agent Systems)

Builds

Long-Running Multi-Agent Harness, Multi-Agent RL Agent infrastructure

Domain

Artificial Intelligence, Reinforcement Learning, Multi-Agent Systems

Deliverable

production ML models

Required skills

Engineering framework development, OS-level multi-task scheduling, multi-process efficiency optimization, asynchronous framework optimization, Coding Agent framework implementation details, full-stack development, containerization, sandboxing

Preferred skills

Language models, Reinforcement Learning theory

Technologies

Multi-Agent RL frameworks, Coding Agents (Claude Code, Codex), Containerization, Sandboxing

Responsibilities

Collaborate with ML colleagues to develop Long-Running Multi-Agent Harness; Assist algorithm teams in building large-scale complex RL environments; Ensure stability of Multi-Agent scenario training and evaluation.

Sourced via bytedance · Listed on CareerPlan, which tracks 845,000+ jobs from 20+ sources.