大模型评测平台研发工程师
Core
Design and build the architecture for a large-scale LLM evaluation platform supporting text, audio, image, video, and Agent models.
Role type
Senior IC backend/platform engineer (LLM evaluation infrastructure)
Builds
Stable, scalable evaluation runtime infrastructure for multi-modal models and applications
Domain
Artificial Intelligence / Large Language Models / Distributed Systems
Deliverable
production ML models
Required skills
Go, Python, Java, C++, distributed system design, microservices, task scheduling, concurrency control, fault tolerance, performance optimization, observability, network communication, LLM concepts (inference, benchmark, RAG, Agent)
Preferred skills
automated evaluation, model judging, 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 task lifecycle management; optimize throughput and latency; establish observability and diagnostic systems; explore automated evaluation and AI-assisted R&D features.
Seniority
Senior, hands-on IC