Member of Technical Staff – AI Inference platform
Core
Architect and implement scalable, reliable, and secure AI inference systems for thousands of concurrent users, ensuring high performance and graceful degradation.
Role type
Senior IC systems engineer (AI inference platform)
Builds
High-throughput model serving stack with request routing, load balancing, and autoscaling across GPU clusters
Domain
AI infrastructure / GPU compute / Model serving
Deliverable
production ML models
Required skills
Go, Python, systems performance engineering, observability, security fundamentals, GPU cluster management
Preferred skills
NVIDIA Dynamo, vLLM, Triton, Kubernetes, multi-region operations
Technologies
Go, Python, Prometheus, Grafana, OpenTelemetry, Kubernetes, vLLM, Triton, TensorRT-LLM, NVIDIA Dynamo
Responsibilities
Architect scalable inference systems, build monitoring and incident response tooling, profile and optimize inference latency, integrate open-source inference frameworks
Seniority
Senior, hands-on IC
