Staff Software Engineer - Backend
Core
Design and evolve infrastructure, platforms, and services enabling machine learning models to run in production at global scale.
Role type
Staff Software Engineer (Backend/ML Infrastructure)
Builds
Scalable, reliable, and observable ML-powered services and platforms
Domain
Cloud Infrastructure & Machine Learning Engineering
Deliverable
production ML models
Required skills
Python, Go, TypeScript, API design, system architecture, scalability, resiliency, performance optimization, CI/CD pipelines, cloud-native application development, containerization, orchestration, GPU infrastructure management, workload scheduling, cloud cost optimization
Preferred skills
Experience with vLLM, Triton, TorchServe, SageMaker Endpoints, OpenTelemetry, Prometheus, Grafana, CloudWatch, vector databases, feature stores, caching technologies (Valkey/Redis), infrastructure-as-code (CDK, CloudFormation, Terraform), AI-assisted development tools
Technologies
vLLM, Triton, TorchServe, SageMaker Endpoints, OpenTelemetry, Prometheus, Grafana, CloudWatch, Valkey, Redis, CDK, CloudFormation, Terraform, Docker, Kubernetes, ECS, EKS, Lambda, DynamoDB, S3, IAM
Responsibilities
Deploy and operate machine learning or generative AI workloads, manage GPU infrastructure and workload scheduling, optimize cloud costs, lead complex technical initiatives, influence architecture, mentor engineers across distributed teams
Seniority
Staff, hands-on IC with leadership responsibilities
