Software Engineer, Sandbox & Agent Executor

About the job

Responsibilities

• Own the behavior of agentic features across multiple product surfaces, focusing on quality, safety, variance, and failure modes.
• Shape the tool and harness surface agents operate against, including MCP servers, sub-agents, and skills.
• Work across product and infrastructure boundaries to shape agent behavior and understand runtime costs.
• Serve as the infrastructure team's technical counterpart on agent workloads.
• Design and evolve prompting, context construction, retrieval, routing, and tool-use strategies for long-horizon workflows.
• Build evaluation systems to measure agent performance through statistical signals, distributions, and trends.
• Detect, diagnose, and resolve non-deterministic failures such as hallucinations, partial correctness, instruction drift, or context sensitivity.
• Partner with product and infrastructure teams on provisioning, isolation, and rollout of agent workloads, including for self-hosted customers.
• Set the pattern for shipping agentic products safely.

Requirements

• 6+ years of professional engineering experience with ownership over complex systems in production.
• 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 in Kubernetes or equivalent in practice (EKS, ECS, or similar), owning services end to end.
• Strong systems thinking with the instinct to use AI as an augment to engineering judgment.
• Curiosity in understanding model outputs and a habit of checking rather than assuming.
• Experience mentoring engineers on AI-related work, including when to rely on models and when not to.
• Experience building for developer surfaces like CLIs, IDE extensions, or coding harnesses (bonus).
• Experience shipping into enterprise or air-gapped environments where direct observation is limited (bonus).