Staff Applied AI Engineer
Core
Deploy, optimize, and scale customer AI models into production, bridging deep inference engineering with customer-facing technical leadership.
Role type
Staff Applied AI Engineer (Managed Inference)
Builds
Production inference endpoints serving billions of tokens daily with optimal latency, throughput, and cost.
Domain
AI Infrastructure / Cloud Computing / Large Language Models
Deliverable
production ML models
Required skills
Inference engines (vLLM, SGLang, TensorRT-LLM), KV-cache tuning, speculative decoding, parallelism, quantization, Kubernetes, Docker, GPU servers, performance profiling, model fine-tuning (LoRA, SFT, DPO), capacity planning, SLO monitoring
Preferred skills
Experience as FDE, solutions engineer, or inference engineer at an AI cloud/lab/provider, open-source model landscape knowledge, hardware-model matching, publishing reference architectures
Technologies
vLLM, SGLang, TensorRT-LLM, Kubernetes, Docker
Responsibilities
Scope workloads and define metrics (TTFT, throughput, cost/token), lead technical POCs, serve as technical lead for customer engineering teams, tune inference engines, profile and diagnose bottlenecks, own end-to-end customer onboarding and deployment, optimize configurations for base/custom/fine-tuned models, feed field insights into product roadmaps
Seniority
Staff, hands-on IC with strategic customer leadership
