Senior Systems Software Engineer - NV Cloud Functions
Core
Building and operating a serverless deployment platform for enabling AI applications, scaling AI inferencing workloads on GPU-backed cloud-agnostic Kubernetes clusters.
Role type
Senior Systems Software Engineer (AI/ML Platform)
Builds
NV Cloud Functions (NVCF) serverless platform for AI inferencing
Domain
Cloud-native AI/ML infrastructure, GPU orchestration, Kubernetes
Deliverable
production ML models
Required skills
Python, Rust, Golang, Linux/Bash, Deep Learning, Machine Learning, AI/DL frameworks (SGLang, vLLM, TensorRT-LLM, Dynamo), CPU/GPU architecture, distributed systems design, software development lifecycle
Preferred skills
HPC, Data Analytics, Open Source contributions, Kubernetes, Slurm, building distributed systems
Technologies
Kubernetes, SGLang, vLLM, TensorRT-LLM, Dynamo, Python, Rust, Golang
Responsibilities
Translate user challenges into product requirements and solutions for AI model delivery; Lead implementation of key features, conduct UAT, load testing, and performance evaluations; Mentor engineering teams on best practices for AI/ML workloads and ML reliability engineering; Produce reference architectures for customer use cases; Shepherd customer issues to resolution; Evaluate new technologies and tooling for the AI-at-scale landscape
Seniority
Senior, hands-on IC with mentorship
