Senior Staff AI Platform Engineer, Infrastructure Services

The role

You will take ownership of the AI Gateway infrastructure to authenticate, route, rate-limit, and monitor AI coding assistant traffic. You will also design solutions across the broader platform stack, including CI/CD, GitOps, and Kubernetes. Additionally, you will host local models and support LLMOps practices.

What you will do

• Architect, harden, and scale the Kong AI Gateway deployment
• Lead reliability and incident response for gateway issues
• Design across the platform including CI/CD, GitOps, and Kubernetes deployment tooling
• Evaluate and roll out AI developer tooling
• Set technical direction and mentor other engineers
• Partner cross-functionally with security, DevEx, and product engineering teams
• Host and operate self-hosted/open-weight model serving infrastructure
• Support the broader model lifecycle including LLMOps practices
• Track usage and cost for both API-based and self-hosted models

Required qualifications

• 8 or more years of experience in platform, infrastructure, or DevOps engineering
• Hands-on experience with API gateway technologies (Kong, Envoy, Apigee, or similar)
• Strong Kubernetes and GitOps experience (ArgoCD or comparable)
• Solid CI/CD background including Jenkins pipeline design and administration
• Experience with artifact and package management systems (Artifactory, Xray, or similar)
• Source control platform administration (GitHub Enterprise)
• Working knowledge of infrastructure-as-code (Terraform)
• Cloud platforms (AWS/EKS)
• Experience deploying and operating self-hosted LLM inference stacks (vLLM, NVIDIA Triton/NIM, TGI, Ollama, or similar)
• Experience with GPU-backed infrastructure, including Kubernetes GPU scheduling and autoscaling
• Familiarity with LLMOps practices
• Clear, proactive communicator

Nice to have

• Direct experience with AI/LLM gateway patterns
• Experience operating LLM/AI-assisted developer tooling at scale (Claude Code, Copilot, or similar)
• Familiarity with Okta/OIDC and enterprise auth patterns
• Experience with engineering productivity metrics tooling (LinearB or similar)
• AI-based code review tooling (Qodo or similar)
• Experience with vector databases and RAG pipelines (e.g., Milvus, Pinecone, pgvector, or similar)
• Exposure to model fine-tuning or lightweight training pipelines (LoRA/QLoRA or similar)

Benefits

• Restricted Stock Units (RSUs)
• Employee Stock Purchase Plan (ESPP)
• Flexible time off
• Paid company holidays and paid sick time
• Gender-neutral parental leave
• Grandparent leave
• Medical, dental, and vision coverage
• 401(k) retirement plan with company match
• Life and disability insurance
• Health and dependent care FSA
• Voluntary benefits (hospital, accident, critical illness)
• Employee Assistance Program (EAP)

About the company

SentinelOne is a company at the intersection of AI and security, pioneering a new operating model for cybersecurity. Their AI-native platform unifies protection across endpoint, cloud, identity, data, and AI systems.