We are looking for a Senior Agentic AI Platform Engineer to help build the shared foundation for production-grade AI agents. This role supports the AI Platform mission: enabling product teams to build, release, evaluate, operate, and scale agentic AI systems without duplicating orchestration, runtime, evaluation, reporting, or reliability work. 

You will work in one of the AI Platform pods, with likely focus across agent orchestration or agent runtime. The work is hands-on and production-oriented: implementation, integration, testing, observability, release discipline, reliability, and post-release support. 

This role is designed for a senior execution engineer who can own meaningful platform systems, work across product and infrastructure boundaries, and help turn agentic AI capabilities into reusable platform patterns. 

What You'll Do 

• Design, build, integrate, test, and operate platform services that support production AI agents across multiple product teams. 

• Implement reusable capabilities for orchestration, runtime execution, tool integrations, observability, reliability, and workflow automation. 

• Partner with product teams, platform teams, QA/Eval, operations, and support stakeholders to release agent capabilities with strong quality and operational readiness. 

• Improve developer tooling, monitoring, logs, metrics, dashboards, alerts, and debugging workflows for agent systems. 

• Support release discipline, regression testing, production support, incident response, and continuous improvement after launch. 

• Identify repeated implementation patterns and help turn them into shared platform capabilities. 

• Contribute to technical designs, code reviews, rollout plans, and reliability improvements across the pod. 

• Mentor engineers through implementation feedback, testing discipline, and practical production judgment. 

What We're Looking For 

• Strong backend or platform engineering experience, especially with distributed systems, infrastructure services, workflow systems, execution platforms, integrations, or developer platforms. 

• Experience building reliable production systems with attention to implementation quality, testing, observability, performance, supportability, and maintainability. 

• Familiarity with asynchronous execution, service coordination, APIs, stateful systems, monitoring, deployment pipelines, or production support. 

• Ability to work in a pod model with clear ownership for delivery, quality, support, and escalation. 

• Interest in LLMs, AI agents, model-driven products, workflow automation, or agentic AI platform patterns. 

• Strong collaboration skills across engineering, product, QA/Eval, operations, and customer-facing teams. 

• Clear communication around technical decisions, implementation plans, risks, and production issues. 

The Ideal Candidate 

The ideal candidate is a strong platform builder who likes turning complex, emerging systems into reliable production infrastructure. They are practical, disciplined, comfortable with ambiguity, and serious about testing, release quality, and post-launch support. 

Why This Role Matters 

AI agent teams move faster when orchestration, runtime, tooling, and reliability patterns are reusable. This role helps reduce duplicated work across teams and makes production-grade AI agents easier to build, release, evaluate, and operate.

#LI-JK1 #LI-REMOTE

• Health, dental, and vision insurance.
• Retirement savings plan with company match.
• Paid time off and holidays.
• Professional development opportunities.
• Performance-based bonus based on position.