Staff AI Platform Engineer

Staff AI Platform Engineer

The Opportunity

We are building AI as a foundational capability across our products and internal operations. We are deploying production AI systems used by millions of customers and leveraged daily by our engineering teams. You will join a growing AI team focused on building the infrastructure, enablement, and foundations that power both internal tools and customer-facing AI experiences. This is not a research or prompt-engineering role. This is a backend platform engineering role with AI at its core. You will partner closely with our Principal AI Architect and other AI engineers to design and scale the systems that make AI reliable, secure, observable, and cost-effective in production.

What You'll Do

AI Service Architecture & Orchestration

• Design and implement AI service layers that abstract model providers (OpenAI, Anthropic, etc.).
• Define patterns for routing, fallback strategies, structured outputs, and tool/function orchestration
• Develop internal APIs and SDKs that product teams can integrate with safely and predictably.
• Ensure model usage is versioned, testable, and production-ready.

AWS Architecture & Platform Design

• Architect AI workloads on AWS (Lambda, ECS/EKS, API Gateway, S3, DynamoDB, etc.).
• Define scalable, cost-efficient system designs capable of supporting large user bases.
• Establish infrastructure patterns, deployment strategies, and system boundaries.
• Partner with DevOps to implement and operate infrastructure, ensuring reliability, security, and operational excellence

AI Data Pipelines & Retrieval Systems

• Build and maintain embedding pipelines and vector search integrations.
• Design ingestion and reprocessing workflows for AI-driven features.
• Support retrieval-augmented generation (RAG) systems at scale.
• Integrate AI systems cleanly into our event-driven backend architecture.

Observability, Safety & Cost Control

• Implement logging, tracing, and monitoring for AI workflows.
• Build cost guardrails and dashboards to manage usage at scale.
• Design fallback and degradation strategies for reliability.
• Ensure secure handling of PII and customer data.

Cross-Team Enablement

• Translate high-level AI feature concepts into clear architectural designs and execution plans
• Provide reference implementations and technical guidance to application teams
• Collaborate closely with DevOps, product, and QA teams to ensure smooth rollout of AI-powered features
• Help establish best practices for how AI is integrated across the organization

What You Bring

• 5+ years of backend or platform engineering experience.
• Experience designing and deploying production systems on AWS.
• Demonstrated experience designing system architecture and partnering with infrastructure/DevOps teams to bring systems into production.
• Hands-on experience integrating AI/LLM services into real applications.
• Strong understanding of scalability, latency, and cost tradeoffs.
• Experience building shared services or internal platforms.
• Strong coding skills in TypeScript/Node.js and/or Python.
• Experience working in distributed systems and integrating third-party APIs.
• Ability to lead execution and bring structure to ambiguous problems.

What You’ll Gain

• Ownership of a critical AI platform surface powering both internal tools and customer-facing features.
• The opportunity to lead execution of AI infrastructure initiatives in a greenfield, high-impact environment.
• Direct partnership with Principal-level architecture leadership and executive visibility.
• Hands-on experience deploying AI systems at scale across high-traffic consumer applications.
• Exposure to real-world tradeoffs in cost, latency, observability, and AI production reliability.
• The ability to shape long-term architectural patterns for how AI is integrated across the organization.
• Autonomy to design, build, and operationalize systems end-to-end in a modern AWS environment.