AI Engineer: Agent Platform & Sandboxed Runtimes

Retool; San Francisco (CA); Hybrid; USD 164,000 - 306,000; Full time

Benefits offered by this job

Hybrid work location

Medical/dental/vision insurance

401(k)

Job summary

Retool is seeking an AI Engineer to build the agent platform behind Retool's AI products and own model-driven behavior in production. You will work across product, infra, and evaluation layers to shape user experiences and ensure reliable, scalable agentic features.

The role involves working with TypeScript, Node.js, and React, across cloud and self-hosted environments, with a strong emphasis on safety, evaluation, and governance.

Qualifications

• 6+ years of professional engineering experience
• Production experience with agentic systems, including context engineering, tool use, and evaluation frameworks
• Hands-on experience with sandboxing technology
• Experience in Kubernetes or equivalent (EKS, ECS, or similar)
• Strong systems thinking and using AI to augment engineering judgment
• Curiosity about model outputs and the habit of checking
• Experience mentoring engineers in this area

Responsibilities

• Own agent behavior across multiple product surfaces, including quality, safety, variance, and failure modes
• Design, build, and deploy agentic products in cloud and self-hosted environments
• Develop evaluation systems and measurement for non-deterministic behavior
• Collaborate with product and infra on provisioning, isolation, and rollout of agent workloads
• Shape prompting, context construction, retrieval, routing, and tool-use strategies for long-horizon workflows

Skills

6+ years exp

Agentic systems

Sandboxing

Kubernetes experience

Context engineering

Evaluation frameworks

Mentoring engineers

Job description

Retool is seeking an AI Engineer to build the agent platform behind Retool's AI products and own model-driven behavior in production. You will work across product, infra, and evaluation layers to shape user experiences and ensure reliable, scalable agentic features.

The role involves working with TypeScript, Node.js, and React, across cloud and self-hosted environments, with a strong emphasis on safety, evaluation, and governance.