大模型评测平台研发工程师
Core
Design and build the architecture and core capabilities of a large model evaluation platform to support text, voice, image, video, and Agent model testing.
Role type
Senior IC platform engineering lead (LLM evaluation infrastructure)
Builds
A stable, scalable evaluation platform for multi-modal models and applications
Domain
Artificial Intelligence / Large Language Models / Infrastructure
Deliverable
production ML models
Required skills
Go, Python, Java, C++, distributed system design, microservices, task scheduling, concurrency control, fault tolerance, performance optimization, network communication, observability, automated testing, LLM concepts (inference, Benchmark, Prompt, RAG, Agent)
Preferred skills
Experience with automated evaluation, model judging, intelligent attribution, AI-assisted R&D
Technologies
Go, Python, Java, C++, microservices, task schedulers, observability tools
Responsibilities
Design platform architecture and core capabilities; Build engineering systems for the full lifecycle of evaluation tasks; Optimize platform throughput, latency, and resource utilization; Establish observability and diagnostic systems; Explore automation and AI-driven evaluation techniques
Seniority
Senior, hands-on IC
