SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Perplexity is building frontier AI agents that can navigate the digital world and perform valuable work for users. The Agents engineering team—comprising backend, full-stack, and AI/ML engineers—is seeking experienced engineers to help design and ship agentic experiences across Perplexity Computer, the Comet ecosystem, the Agent API, and more.
In this role, you will work at the intersection of applied research and engineering to solve open problems in AI agents. You'll engineer agent harnesses that connect powerful models with environments and tools, design AI agents to navigate digital interfaces and accomplish user-specified objectives, and develop training pipelines for action and decision models that operate on complex multimodal states. You'll also work on permission architectures, payload classifiers, and secure-by-design agentic capabilities, while ensuring excellent experiences across desktop, mobile, headless cloud, and other environments.
Key responsibilities include:
- Engineer agent harnesses connecting models with required environments and tools
- Drive cutting-edge AI capabilities across multiple product layers in the rapidly growing AI agents space
- Develop and leverage frontier AI models, infrastructure, and browser technologies to advance capability and scale for a growing userbase
- Maintain high craft and quality standards in both AI agent performance and user experience
- Collaborate with engineers, designers, product managers, data scientists, and others to integrate core Perplexity functionality into agentic products
- Contribute to product reliability, code quality, AI evaluation, testing, and maintenance
Requirements:
- Strong foundational familiarity with the full AI product stack
- Proficiency in Python (bonus: TypeScript, Go, and/or Rust)
- Significant experience in at least one of: context engineering and tool interfaces for frontier AI models; post-training and reinforcement learning (particularly for multimodal models); or browser technologies (CDP, Playwright, extension development, etc.)
- Strong product intuition and taste for user experience excellence
- Comfortable working with a small, fast-moving team; must be willing to dive in and take ownership
- Passion for shipping products that surprise and delight
