AI Agent Systems Engineer (AI)

Location: San Francisco or New York City, United States

Salary: $220,000–$405,000 per year, plus equity; USD ranges apply only to U.S.-based positions.

Company

Perplexity builds AI products that transform knowledge into action, including agentic AI experiences used by millions of people.

What you will do

• Evaluate frontier models on real user tasks, identify useful behaviors and failure modes, and take promising capabilities from prototyping and evaluation through production launch, monitoring, and iteration.
• Improve agent planning, tool use, context management, error recovery, and reliable completion of long-running tasks.
• Design scalable agent capabilities including skills, plugins, artifact generation, tool integration, auto-research, and multi-agent collaboration.
• Own agent behavior end-to-end across user-facing interfaces, backend services, models, prompts, harnesses, and products.
• Define offline and online evaluations for task completion, correctness, safety, latency, cost, and user satisfaction.
• Build secure, observable, and reliable systems with permissions, safeguards, tracing, replay, and monitoring for reproducible agent failures.

Requirements

• Typically 6+ years of professional software engineering experience, with a track record of building and owning robust AI-powered, large-scale, user-facing or data-intensive products; exceptional candidates with less experience and outstanding impact may be considered.
• Strong software engineering fundamentals and experience building and operating AI/ML products, backend services, or distributed systems at scale.
• Experience owning the AI product lifecycle, including data analysis, rigorous evaluation, production monitoring, iterative improvement, metrics, production data, and user feedback.
• Practical experience in one or more of agent harnesses, tool use, context engineering, model evaluation, browser automation, or long-running task execution.
• Strong product judgment and execution, including translating ambiguous user needs into applied AI or ML problems and shipping durable solutions with measurable user impact.
• Genuine interest in frontier AI capabilities and agent systems, with enthusiasm for rapidly exploring, evaluating, and productizing new model behaviors.

Nice to have

• Experience with LLM context engineering or harness engineering, subagents, coding assistants, and long-running or autonomous task execution.
• Deep familiarity with current model families across reasoning, tool use, context management, and long-horizon tasks.
• Experience building agent permissions, safeguards, evaluation infrastructure, or production observability systems.
• Experience with mid-training, post-training, or reinforcement learning for frontier or open-source models.
• AI/ML research experience demonstrated through publications, open-source contributions, or other meaningful research impact.
• Experience at a fast-growing startup or on a high-ownership engineering team.

Culture & Benefits

• Culture emphasizes craftsmanship, ownership, entrepreneurship, scholarship, and partnership.
• U.S. full-time employees receive equity, health, dental, vision, retirement, fitness, commuter, and dependent care benefits.
• Full-time employees outside the U.S. receive benefits tailored to their region of residence.
• Technology stack includes Python, Go, Rust, PostgreSQL, DynamoDB, AWS, and TypeScript.