Member of Technical Staff Applied AI Engineer Agent Capabilities

You will evaluate frontier models against real user tasks and turn promising capabilities into reliable production agent systems. You will improve planning, tool use, context management, error recovery, and long-running task execution. You will define evaluations, monitoring, safeguards, tracing, and replay infrastructure, then iteratively improve agent behavior across models, prompts, and products.

Responsibilities

• Evaluate frontier models and convert promising behaviors into production agent systems
• Improve agent planning, tool use, context management, error recovery, and long-running task execution
• Design scalable agent capabilities and their supporting architecture
• Define offline and online evaluations for correctness, safety, latency, cost, and user satisfaction
• Build secure, observable agent systems with permissions, safeguards, tracing, replay, and monitoring
• Collaborate with product, data science, and research partners to deliver reliable product experiences
• Set technical direction, conduct design reviews, and provide mentorship

Requirements

• 6+ years of professional software engineering experience
• Experience building and owning robust AI-powered, large-scale, user-facing, or data-intensive products
• Experience building and operating AI/ML products, backend services, or distributed systems at scale
• Experience owning the AI product lifecycle, including data analysis, evaluation, monitoring, and iterative improvement
• Experience with agent harnesses, tool use, context engineering, model evaluation, browser automation, or long-running task execution
• Strong product judgment and execution

Benefits

• Equity
• Health insurance
• Dental insurance
• Vision insurance
• Retirement benefits
• Fitness benefits
• Commuter account
• Dependent care account
• Region-tailored benefits for eligible international full-time employees