Senior Software Engineer (Serverless)
Core
Design and build core components of a GPU-native serverless AI platform for deploying inference endpoints and batch jobs without managing infrastructure.
Role type
Senior Software Engineer (Serverless AI Platform)
Builds
Control plane, scheduler, runtime, autoscaler, and APIs for GPU workloads
Domain
Cloud Infrastructure / AI / Distributed Systems
Deliverable
production ML models | infrastructure
Required skills
Golang, Kubernetes, distributed systems, high-throughput low-latency services, SRE practices, customer architecture reviews
Preferred skills
Serverless/FaaS platforms, GPU scheduling, ML inference optimization, cold-start optimization, Kubernetes operators, open-source contributions
Technologies
Golang, Kubernetes, vLLM, TensorRT-LLM, Triton Inference Server, FireCracker, gVisor
Responsibilities
Design and build core platform components; solve hard engineering problems like cold-start latency and GPU scheduling; set technical direction and architecture; conduct code and design reviews; run the service as an SRE; work directly with customers on production issues; partner with Product and infrastructure teams
Seniority
Senior, high-ownership IC