MaaS模型评测高级工程师
Core
Build and maintain quality assurance and evaluation systems for Tencent Cloud MaaS products, focusing on model benchmarking, risk identification, and stability assurance.
Role type
Senior Machine Learning Engineer (Model Evaluation & Quality Assurance)
Builds
Model evaluation platforms, benchmark datasets, and automated evaluation pipelines for large language models.
Domain
Artificial Intelligence / Large Language Models
Deliverable
production ML models
Required skills
Python development, large model training, model evaluation methodologies, inference frameworks (sglang, vllm), benchmark data integration
Preferred skills
Prompt Engineering (PE) practice, project management experience, team leadership
Technologies
Python, sglang, vllm, SWE-bench, HumanEval, MMLU, AgentBench, kimi, deepseek, minimax, glm
Responsibilities
Establish stability assurance systems for the full product lifecycle, construct model evaluation frameworks and datasets, track industry benchmark dynamics, build automated evaluation tools and platforms.
