Member of Technical Staff – AI Inference platform, features
Core
Design and ship new capabilities for Lyceum's AI inference platform, including model serving configurations, API surfaces, and developer experience tools.
Role type
Senior IC backend engineer (AI inference platform)
Builds
AI inference platform features, API surfaces, and developer tools
Domain
Cloud infrastructure + AI/ML inference
Deliverable
product features
Required skills
Go, Python, ML inference serving frameworks (vLLM, TGI), REST/gRPC API design, backend systems, production deployment of LLMs
Preferred skills
GPU scheduling, inference optimization (quantization, speculative decoding), Kubernetes, container orchestration, AI model format conversion (GGUF, SafeTensors, ONNX), platform engineering
Technologies
Go, Python, vLLM, TGI, Kubernetes, REST, gRPC
