Staff Platform Engineer Service Infrastructure
Together AIVisit Together AI website
Together AI operates an AI-native cloud platform for open and custom AI models.
San Francisco, United States
About Together AI
Together AI provides production AI infrastructure spanning inference, accelerated compute, model training and fine-tuning, and secure code sandboxes for AI development.
Skills
Candidate Availability
Required and preferred rules are kept separate and reflect the wording in the original posting.
About the Role
You will lead the technical direction for Product Foundations service infrastructure. You will improve reliability, deployment safety, operability, and production readiness; create reusable infrastructure patterns; and coordinate standards across platform, infrastructure, networking, and security stakeholders.
Requirements
- 7+ years of professional experience in platform engineering, service infrastructure, SRE, distributed systems, cloud infrastructure, or related roles
- Production experience with Kubernetes, including EKS, Helm, ArgoCD, ingress, autoscaling, secrets, service identity, networking, and progressive delivery
- Terraform experience, including module design, infrastructure CI/CD, policy enforcement, production applies, and self-service workflows
- Experience operating CDNs, load balancers, DNS, TLS, ingress and egress controls, and traffic management
- Proficiency in Go, Python, TypeScript, or a similar infrastructure tooling language
- AWS experience, including EKS, IAM, VPC networking, load balancing, Route 53, CloudFront, and ECR
- Experience with observability systems, including metrics, logs, traces, dashboards, alerting, SLOs, and incident response
- Ability to lead cross-functional technical initiatives
- Written communication skills for design documents, migration plans, operational guidance, and technical standards
Responsibilities
- Own the technical direction for service infrastructure within Product Foundations
- Improve service reliability, operability, deployment safety, infrastructure consistency, and production readiness
- Partner on networking, DNS, CDN, load balancing, delivery, and gateway patterns
- Drive cross-company infrastructure initiatives
- Build reusable infrastructure primitives, including Helm charts, Terraform modules, GitHub Actions and GitOps workflows, service scaffolding, runbooks, and documentation
- Establish technical standards through design documents, architecture reviews, mentorship, and hands-on implementation
Benefits
- Startup equity
- Health insurance