AI Platform Engineer
Core
Design and build an end-to-end AI model service platform from scratch to reliably serve hundreds of thousands to millions of users.
Role type
Senior AI Platform Engineer
Builds
Unified layer of model API interfaces and scalable inference services for connected hardware
Domain
AI/ML infrastructure, Cloud-native backend systems
Deliverable
production ML models
Required skills
Backend development (Java, Go, Python), Cloud platform expertise (AWS, Azure, GCP, Alibaba Cloud), Microservices architecture, API design, AI/LLM API integration, Inference frameworks (vLLM, Triton, TGI), Distributed systems, Load balancing, Service routing
Preferred skills
None stated
Technologies
vLLM, Triton, TGI, OpenAI, Anthropic, Qwen, AWS, Azure, GCP, Alibaba Cloud, Java, Go, Python
Responsibilities
Architect and scale unified model API interfaces, manage request routing and load balancing, build systems for high user volumes, partner with Agent and hardware teams
Seniority
Senior, hands-on IC
