SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Perplexity AI is seeking a Software Engineer to evolve the core agent harness powering its flagship answer engine and agentic AI product, Computer. In this role, you will combine strong product judgment with single- and multi-agent engineering paradigms to build reliable, scalable agents capable of accumulating knowledge and answering complex societal questions.
You will translate user needs and quantitative insights into improvements across agent orchestration, context management, performance, and reliability. The ideal candidate understands that reliable agents at global scale require excellent observability, rigorous evaluation, and developer experience that enables autonomous failure reproduction and fixing through methods like autoresearch.
The harness you build will power both production experiences and the training/evaluation of new models, creating a tight feedback loop between real-world usage and model improvement—central to Perplexity's mission.
Required qualifications include 2+ years building and shipping large-scale AI systems with high reliability, availability, and performance. You should demonstrate strong software engineering craft with attention to developer experience and designing systems that evolve with a rapidly advancing AI landscape. Proficiency in Python is required; experience with Rust and cloud infrastructure (AWS, Kubernetes) is a bonus. A BS, MS, or PhD in Computer Science, Engineering, or related field (or equivalent experience) is expected.
Perplexity values craftsmanship, ownership, entrepreneurship, scholarship, and partnership. Engineers identify problems, design solutions, and ship them with urgency while working among highly talented peers pursuing knowledge and truth.
About Perplexity AI
AI / Data / Infrastructure — AI answer engine and search product for consumers and enterprises.
