Senior AI Engineer

We are hiring a Senior AI Engineer to build and operate production AI systems and infrastructure.

In this role, you will work on AI agents, MCP servers, agent evaluation, and Temporal-based workflow frameworks.

Responsibilities

• Build and deploy AI agents that use tools, call services, manage context, and execute multi-step tasks.
• Develop and maintain MCP servers and tool integrations used by internal AI systems.
• Build workflow infrastructure using Temporal or similar orchestration frameworks.
• Design and implement agent evaluation flows, test suites, quality metrics, and feedback loops. Design backend services, APIs, persistence layers, and platform components for AI applications.
• Work with SQL and NoSQL databases, queues, distributed systems, and cloud-native infrastructure.
• Build CI/CD pipelines, Docker images, Kubernetes deployments, monitoring, and operational tooling.
• Debug production issues across services, workflows, agents, tools, models, and infrastructure.
• Collaborate with engineering, product, infrastructure, and data science teams to turn requirements into reliable systems.

Requirements

• 5+ years of experience and a practical understanding of how AI agents are built, including tool use, state, context, and multi-step execution.
• Bachelors degree or equivalent experience.
• Experience with at least one open-source agent or LLM application framework, such as LangChain/LangGraph.
• Strong software engineering background, especially in backend development.
• Experience with distributed systems, workflow orchestration, and production service design.
• Hands-on experience with SQL and NoSQL databases.
• Experience with Docker, Kubernetes, CI/CD pipelines, and production deployment workflows.

Nice to Have

• Experience working with both traditional machine learning systems and contemporary LLM or agentic applications.
• Excellent judgment about when agent-based approaches are appropriate,and when a simpler solution is more effective.
• Experience making AI behavior measurable, observable, explainable, and safe in production.
• Experience optimizing inference systems for performance, infrastructure efficiency, and operating cost.
• A history of guiding engineers or heading cross-departmental technical projects.