Agent Platform Engineer

ZoomSeattle, WA
5dHybrid

About The Position

Agent Platform Engineer (Autonomous Agents & AI Engineer) What you can expect We're seeking an experienced Agent Platform Engineer to join our AI engineering team. You'll play a critical role in designing, building, and scaling the platform that powers autonomous and agentic AI systems across our products. Focus on building systems and infrastructure that enable agents to reason, act, and operate reliably in production. You'll collaborate closely with ML researchers, product teams, and application engineers to transform agent prototypes into robust, production-grade platforms. About the Team The AI Agent Team is focused on enabling the next generation of AI-driven productivity through agentic systems. We build platforms enabling teams to deploy intelligent agents at the intersection of AI, infrastructure, and developer experience. We value engineers who can bridge research ideas with real-world scalability and reliability.

Requirements

  • Demonstrate Bachelor's in Computer Science, Engineering, or a related technical field (or equivalent practical experience).
  • Have 3+ years of experience in software engineering, platform engineering, or infrastructure roles.
  • Need experience building production backend or distributed systems.
  • Demonstrate proficiency in Python, Go, Java, or similar languages, combined with solid system design skills.
  • Have hands-on experience deploying and operating systems on cloud infrastructure (Kubernetes, Docker, AWS/GCP/Azure).
  • Need to be familiarity with LLM-powered systems, agent frameworks, or AI infrastructure in production environments.

Responsibilities

  • Designing and implementing agent execution platforms that support reasoning, planning, and long running task orchestration.
  • Building core services for agent memory, state management, tool invocation, sandbox and lifecycle management.
  • Developing platform abstractions and APIs that enable teams to build and deploy agents consistently.
  • Partnering with ML and research teams to productionize LLM- and agent-based workflows.
  • Implementing observability, evaluation, and debugging frameworks for agent behavior and performance.
  • Optimizing agent infrastructure for low latency, high throughput, and reliability at scale.
  • Implementing safety, guardrails, and control mechanisms for autonomous agent execution.
  • Leveraging AI-assisted coding tools to accelerate development, testing, and iteration
© 2024 Teal Labs, Inc
Privacy PolicyTerms of Service