AI Software Engineer - Agent Platform

Details

Perplexity is seeking an experienced AI Agent Software Engineer to help revolutionize the way people search and interact online. In this role, you'll build a scalable and elastic agent platform to power a wide span of agent workloads from search to research to browser.

Responsibilities

• Architect and implement the next-generation agent platform that powers all agentic products at Perplexity with high efficiency, reliability, and scalability.
• Stay up-to-date on new features released by external LLM providers and in-house researchers and provide unified interfaces to interact with different sizes of models.
• Improve the speed and quality of the AI agent codebase and engineering processes to ensure consistent delivery of an excellent product experience.
• Maintain a high quality bar to build generalized agentic and AI evaluation systems to power product online and offline evaluations.
• Collaborate across disciplines, including researchers, engineers, product managers, and designers, to close gaps and ship products.

Requirements

• Past experience building agent applications, including work with tool calling, MCP, and context engineering.
• Ability to make trade-offs when using different models to achieve goals with the most cost-efficient and reliable system design.
• Self-motivated with a willingness to take ownership of platform components.
• 4+ years of industry experience.
• Preferred: past experience with open source LLM post-training and evaluation.

Compensation

• Cash compensation range: $200,000 - $300,000 per year.
• Final offer amounts are determined by multiple factors, including experience and expertise, and may vary from the amounts listed above.
• Equity: In addition to base salary, equity may be part of the total compensation package.

Benefits

• Comprehensive health, dental, and vision insurance for you and your dependents.
• Includes a 401(k) plan.

Location & Work Style

• Hybrid role based in San Francisco.