AI Engineer, Sandbox & Agent Platform (Production)

Retool Inc.; San Francisco (CA); On-site; USD 164,000 - 270,000; Full time

Job summary

Retool Inc. 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 the product, infrastructure, and evaluation layers to shape user experiences and confidence in deployments. You’ll own agentic features across multiple product surfaces, collaborate with infra teams on runtime costs, and design prompting, context construction, retrieval, routing, and tool-use strategies for long-horizon workflows.

Qualifications

• 6+ years of professional engineering experience in production systems.
• 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).
• Strong systems thinking with AI as augmentation, not replacement.
• Experience mentoring engineers in this domain.

Responsibilities

• Own the behavior of agentic features across product surfaces, including quality, safety, variance, and failure modes.
• Collaborate with product and infra teams on deployment, cost, and reliability of agent workloads.
• Design prompting, context construction, retrieval, routing, and tool-use strategies for long-horizon workflows.
• Build evaluation systems measuring performance via statistical signals, distributions, and trends.
• Detect, diagnose, and resolve non-deterministic failures in production.
• Partner with teams on self-hosted deployments and rollout patterns.

Skills

6+ years exp

Agentic systems

Context engineering

Tool use

Kubernetes

Sandboxing

Systems thinking

Mentoring

Tools

Kubernetes

EKS

ECS

Job description

Retool Inc. 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 the product, infrastructure, and evaluation layers to shape user experiences and confidence in deployments. You’ll own agentic features across multiple product surfaces, collaborate with infra teams on runtime costs, and design prompting, context construction, retrieval, routing, and tool-use strategies for long-horizon workflows.