豆包大模型Agent算法工程师 - 火山方舟
Core
Design and optimize the architecture and runtime mechanisms for managed AI agents and harnesses within a large-scale model platform.
Role type
Senior IC Agent Algorithm Engineer
Builds
Managed-Agent platform features, including harness architecture, tool integration, and multi-agent collaboration systems.
Domain
AI / Large Language Models / Agent Systems
Deliverable
production ML models
Required skills
Agent Harness optimization, LLM API integration, Reasoning, KV Cache, ToolUse, Skills, ReAct, Multi-Agent, MCP, A2A, FunctionCalling, RAG, Agent evaluation, Software development with AI assistance
Preferred skills
Experience with AutoPE, Memory Evolve, Harness code evolution (e.g., AlphaEvolve, Hyper-Agents), deep usage of commercial agent products (OpenClaw, HermesAgent, Codex, ClaudeCode, Managed-Agents)
Responsibilities
Select and design harness technical architecture, optimize harness runtime modes and context mechanisms, build end-to-end agent evaluation frameworks, define and implement frontier innovations in harness evolution
Seniority
Senior, hands-on IC