Senior AI Agent Engineer — Sandbox & Runtime

Socket.dev; San Francisco (CA); On-site; USD 180,000 - 280,000; Full time

Job summary

Socket.dev in San Francisco is seeking an AI Engineer to build the agent platform behind AI products and own model-driven behavior in production. You will work across the product, infrastructure, and evaluation layers to shape user experience and shipping reliability.

You will tackle non-deterministic issues, design prompting and evaluation systems, and collaborate with product and infra teams on deploying agent workloads in cloud and self-hosted environments.

Qualifications

• Must have 6+ years of professional engineering experience with ownership over complex systems in production.
• Proven production experience with agentic systems, including context engineering, tool use, and evaluation frameworks at real user scale.
• Hands-on experience with sandboxing technology and running agents inside sandboxed environments.
• Experience mentoring engineers on this kind of work and when to lean on a model.

Responsibilities

• Own the behavior of agentic features across multiple product surfaces, including quality, safety, variance, and failure modes.
• Design, build, and deploy agentic products across cloud and self-hosted environments.
• Shape prompting, context construction, retrieval, routing, and tool-use strategies for long-horizon workflows and build evaluation systems.
• Detect, diagnose, and resolve non-deterministic failures such as hallucinations, instruction drift, or context sensitivity.

Skills

6+ yrs experience

Agentic systems

Sandboxing

Systems thinking

Mentoring

Curiosity

Tools

Kubernetes

Job description

Socket.dev in San Francisco is seeking an AI Engineer to build the agent platform behind AI products and own model-driven behavior in production. You will work across the product, infrastructure, and evaluation layers to shape user experience and shipping reliability.

You will tackle non-deterministic issues, design prompting and evaluation systems, and collaborate with product and infra teams on deploying agent workloads in cloud and self-hosted environments.