CareerPlanSign in

模型训练-大模型安全群组

成都💼 Full-time🗓 2026-09-28

Core

Develops prompt engineering strategies, builds agents, and operates automated evaluation systems to ensure large language model safety and compliance.

Role type

Senior LLM Safety Engineer (Prompt Engineering & Evaluation)

Builds

Automated evaluation suites, safety testing frameworks, and agent-based safety mechanisms

Domain

Artificial Intelligence / Large Language Models / Content Safety

Deliverable

production ML models

Required skills

Python, SQL, Prompt Engineering, Agent Development, Automated Scripting, Model Evaluation, Data Analysis

Preferred skills

LLM training experience, AI platform operations, Robustness testing

Technologies

Python, SQL, LLM platforms

Responsibilities

Write prompts and build agents to enhance model safety; Operate automated evaluation tasks and generate assessment reports; Explore novel prompt attack vectors and build comprehensive safety testing systems; Conduct online product security inspections and close risk loops; Analyze data to optimize delivery processes and quality.

Sourced via bytedance · Listed on CareerPlan, which tracks 877,000+ jobs from 20+ sources.