Member of Technical Staff (software Engineer, Applied Ai)

Perplexity Perplexity · AI Frontier · San Francisco, CA · AI

Applied AI Engineer to design, build, and iterate on cutting-edge agents powering the core experience in Perplexity Computer. This role involves developing frontier context layer applications, personalization, recommendations, and monetization applications, as well as building agent capabilities. The engineer will own the full model lifecycle from research to production, including data analysis, modeling, evaluation, A/B testing, and iterative improvement, and will also build an auto research harness for agent exploration. Collaboration with cross-functional teams and staying updated on AI innovation are key.

What you'd actually do

  1. Apply state-of-the-art ML and LLM techniques to solve problems spanning: Personalization (LLM memory, context summarization, retrieval and ranking); Contextual recommendations and Monetization applications; Build frontier agent capabilities on top of Perplexity Computer
  2. Build auto research harness for both offline and online techniques, designing experiments and metrics that provide deep insight into quality and impact.
  3. Own the entire model lifecycle from research to production: data analysis, modeling, evaluation, offline/online A/B testing, and iterative improvement and build autonomous harness for agent squad to explore different problem spaces.
  4. Collaborate cross-functionally with engineers, PMs, data scientists, and designers to ensure our AI drives meaningful product improvements.
  5. Stay at the forefront of ML/AI innovation by evaluating and incorporating emerging research and algorithms into the product lifecycle.

Skills

Required

  • Python
  • production-quality codebases
  • collaborative development
  • agentic coding tools for large scale parallel developments
  • data analysis
  • rigorous evaluation
  • ongoing monitoring/improvement
  • cross-functional teams

Nice to have

  • LLM context engineering
  • harness engineering
  • mid-training or post-training frontier open source models
  • large scale user-centric and content-centric personalization challenges (user modeling, retrieval, content ranking, etc)

What the JD emphasized

  • 5+ years experience building and shipping robust AI products for large-scale, user-facing or data-driven products.
  • In-depth experience with the full AI lifecycle: data analysis, rigorous evaluation, and ongoing monitoring/improvement.

Other signals

  • design, build, and iterate on cutting-edge agents
  • develop frontier context layer applications
  • Own the entire model lifecycle from research to production
  • evaluating and incorporating emerging research and algorithms into the product lifecycle